List of Publications about Slow Feature Analysis
(compiled by Laurenz Wiskott)

This list contains references to publications about Slow Feature Analysis, including those that build on and extend SFA or that compare such publications to others conceptionally, analytically in terms of mathematics or experimentally in terms of performance.

You can limit the list by search terms. You can use the Global QuickSearch or simply enter a search term into the respective fields on top of any column. If you don't want QuickSearch to search in abstracts (where available) as well, you can disable this via the 'Search Settings' button to the right. Note that you can use regular expressions in your search if you want to. For instance to search for entries between 1990 and 1993, type '199[0-3]' in the Global QuickSearch, or for entries written by either turner or Schrauwen type 'Turner|Schrauwen' in the author search field.

You can also sort all entries in ascending or descending order by clicking once or twice, respectively, on a column's title. For instance, to sort by the year published, simply click on 'Year' in the top field of the year column.

If available, the Title fields also allow you to quickly access the BibTeX entry, Abstract, or link to a .pdf version of the respective paper. [URL] usually refers to an official link to an abstract or full paper; [URL(2)] usually refers to an inofficial full paper preprint version; [URL(3)] usually refers to some additional material, such as a poster. (Notice that some official full papers have copyright restrictions, e.g. Neural Computation. You may copy them but not post them somewhere else.)

Please send missing references and corrections to Laurenz Wiskott (see my homepage for the email address).

Author	Year	Title	Reference	BibTeX type
de Alcântara, M.F.; Moreira, T.P. & Pedrini, H.	2013	Motion silhouette-based real time action recognition [Abstract] [BibTeX] [URL] [URL(2)]	Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications , 471-478. Publ. Springer Nature.	incollection
Abstract: Most of the action recognition methods presented in the literature cannot be applied to real life situations. Some of them demand expensive feature extraction or classification processes, some require previous knowledge about starting and ending action times, others are just not scalable. In this paper, we present a real time action recognition method that uses information about the variation of the silhouette shape, which can be extracted and processed with little computational effort, and we apply a fast configuration of lightweight classifiers. The experiments are conducted on theWeizmann dataset and show that our method achieves the state-of-the-art accuracy in real time and can be scaled to work on different conditions and be applied several times simultaneously.
BibTeX: @incollection{AlcantaraMoreiraEtAl-2013, author = {de Alc{\^a}ntara, Marlon F and Moreira, Thierry P and Pedrini, Helio}, title = {Motion silhouette-based real time action recognition}, booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications}, publisher = {Springer Nature}, year = {2013}, pages = {471--478}, url = {http://link.springer.com/chapter/10.1007/978-3-642-41827-3_59}, url2 = {https://www.researchgate.net/profile/Marlon_Alcantara3/publication/296658600_Motion_Silhouette-Based_Real_Time_Action_Recognition/links/57675b8508aeb4b9980981eb.pdf}, doi = {http://doi.org/10.1007/978-3-642-41827-3_59} }
Antonelo, E.	2011	Reservoir computing architectures for modeling robot navigation systems [Abstract] [BibTeX] [URL] [URL(2)]	Ghent University, Ghent University .	phdthesis
Abstract: Robot Navigation Systems Autonomous mobile robots must be able to safely and purposefully navigate in complex dynamic environments, preferentially considering a restricted amount of computational power as well as limited energy consumption. In order to turn these robots into commercially viable domestic products with intelligent, abstract computational capabilities, it is also necessary to use inexpensive sensory apparatus such as a few infra-red distance sensors of limited accuracy. Current state-of-the-art methods for robot localization and navigation require fully equipped robotic platforms usually possessing ex- pensive laser scanners for environment mapping, a consider- able amount of computational power, and extensive explicit modeling of the environment and of the task. This thesis The research presented in this thesis is a step towards creating intelligent autonomous mobile robots with abstract reasoning capabilities using a limited number of very simple raw noisy sensory signals, such as distance sensors. The basic assumption is that the low-dimensional sensory signal can be projected into a high-dimensional dynamic space where learn- ing and computation is performed by linear methods (such as linear regression), overcoming sensor aliasing problems com- monly found in robot navigation tasks. This form of computa- tion is known in the literature as Reservoir Computing (RC), and the Echo State Network is a particular RC model used in this work and characterized by having the high-dimensional space implemented by a discrete analog recurrent neural net- work with fading memory properties. This thesis proposes a number of Reservoir Computing architectures which can be used in a variety of autonomous navigation tasks, by model- ing implicit abstract representations of an environment as well as navigation behaviors which can be sequentially executed in the physical environment or simulated as a plan in deliberative goal-directed tasks. Navigation attractors A navigation attractor is a reactive robot behavior defined by a temporal pattern of sensory-motor cou- pling through the environment space. Under this scheme, a robot tends to follow a trajectory with attractor-like charac- teristics in space. These navigation attractors are character- ized by being robust to noise and unpredictable events and by having inherent collision avoidance skills. In this work, it is shown that an RC network can model not only one behavior, but multiple navigation behaviors by shifting the operating point of the dynamical reservoir system into different sub-space attractors using additional external inputs representing the se- lected behavior. The sub-space attractors emerge from the coupling existing between the RC network, which controls the autonomous robot, and the environment. All this is achieved under an imitation learning framework which trains the RC network using examples of navigation behaviors generated by a supervisor controller or a human. Implicit spatial representations From the stream of sensory in- put given by distance sensors, it is possible to construct im- plicit spatial representations of an environment by using Reser- voir Computing networks. These networks are trained in a supervised way to predict locations at different levels of ab- straction, from continuous-valued robot’s pose in the global coordinate’s frame, to more abstract locations such as small delimited areas and rooms of a robot environment. The high- dimensional reservoir projects the sensory input into a dy- namic system space, whose characteristic fading memory dis- ambiguates the sensory space, solving the sensor aliasing prob- lems where multiple different locations generate similar sen- ....
BibTeX: @phdthesis{Antonelo-2011, author = {Antonelo, Eric}, title = {Reservoir computing architectures for modeling robot navigation systems}, school = {Ghent University}, year = {2011}, url = {https://biblio.ugent.be/publication/3177516/file/4335735}, url2 = {https://www.researchgate.net/profile/Eric_Antonelo/publication/292349529_Reservoir_computing_architectures_for_modeling_robot_navigation_systems/links/578a44ed08ae7a588eebc221.pdf} }
Antonelo, E.A. & Schrauwen, B.	2009	Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Artificial Neural Networks , 747-756.	inproceedings
Abstract: Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal’s environment). This work seeks to model these place cells by employing three (biologically plausible) techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA). The proposed architecture is composed of three layers, where the bottom layer is a dynamic reservoir of recurrent nodes with fixed weights. The upper layers (SFA and ICA) provides a self-organized formation of place cells, learned in an unsupervised way. Experiments show that a simulated mobile robot with 17 noisy short-range distance sensors is able to self-localize in its environment with the proposed architecture, forming a spatial representation which is dependent on the robot direction.
BibTeX: @inproceedings{AntoneloSchrauwen-2009a, author = {Antonelo, Eric A and Schrauwen, Benjamin}, title = {Unsupervised learning in reservoir computing: modeling hippocampal place cells for small mobile robots}, booktitle = {International Conference on Artificial Neural Networks}, year = {2009}, pages = {747--756}, url = {http://link.springer.com/chapter/10.1007/978-3-642-04274-4_77}, url2 = {https://pdfs.semanticscholar.org/a3bb/f2e5c0a5440f7bf1557a55918845dc39bd30.pdf}, doi = {http://doi.org/10.1007/978-3-642-04274-4_77} }
Antonelo, E.A. & Schrauwen, B.	2009	On different learning approaches with echo state networks for localization of small mobile robots [Abstract] [BibTeX] [URL] [URL(2)]	Anais do 9. Congresso Brasileiro de Redes Neurais . Publ. Associacao Brasileira de Inteligencia Computacional - ABRICOM.	inproceedings
Abstract: Animals such as rats have innate and robust localization capabilities which allow them to navigate to goals in a maze. The rodent’s hippocampus, with the so called place cells, is responsible for such spatial processing. This work seeks to model these place cells using either supervised or unsupervised learning techniques. More specifically, we use a randomly generated recurrent neural network (the reservoir) as a non-linear temporal kernel to expand the input to a rich dynamic space. The reservoir states are linearly combined (using linear regression) or, in the unsupervised case, are used for extracting slowly-varying features from the input to form place cells (the architectures are organized in hierarchical layers). Experiments show that a small mobile robot with cheap and low-range distance sensors can learn to self-localize in its environment with the proposed systems.
BibTeX: @inproceedings{AntoneloSchrauwen-2009b, author = {Antonelo, Eric Aislan and Schrauwen, Benjamin}, title = {On different learning approaches with echo state networks for localization of small mobile robots}, booktitle = {Anais do 9. Congresso Brasileiro de Redes Neurais}, publisher = {Associacao Brasileira de Inteligencia Computacional - {ABRICOM}}, year = {2009}, url = {http://abricom.org.br/eventos/cbrn_2009/067_CBRN2009/}, url2 = {http://snn.elis.ugent.be/sites/snn/files/papers/CBRN2009_eric.pdf}, doi = {http://doi.org/10.21528/cbrn2009-067} }
Antonelo, E. & Schrauwen, B.	2009	Towards autonomous self-localization of small mobile robots using reservoir computing and slow feature analysis [Abstract] [BibTeX] [URL]	2009 IEEE International Conference on Systems, Man and Cybernetics , 3818-3823. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Biological systems such as rats have special brain structures which process spatial information from the envi- ronment. They have efficient and robust localization abilities provided by special neurons in the hippocampus, namely place cells. This work proposes a biologically plausible architecture which is based on three recently developed techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA). The bottom layer of our RC-SFA architecture is a reservoir of recurrent nodes which process the information from the robot’s distance sensors. It provides a temporal kernel of rich dynamics which is used by the upper two layers (SFA and ICA) to autonomously learn place cells. Experiments with an e-puck robot with 8 infra-red sensors (which measure distances in [4-30] cm) show that the learning system based on RC-SFA provides a self-organized formation of place cells that can either distinguish between two rooms or to detect the corridor connecting them.
BibTeX: @inproceedings{AntoneloSchrauwen-2009, author = {Antonelo, Eric and Schrauwen, Benjamin}, title = {Towards autonomous self-localization of small mobile robots using reservoir computing and slow feature analysis}, booktitle = {2009 {IEEE} International Conference on Systems, Man and Cybernetics}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2009}, pages = {3818--3823}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.705.3724&rep=rep1&type=pdf}, doi = {http://doi.org/10.1109/icsmc.2009.5346617} }
Antonelo, E. & Schrauwen, B.	2010	Learning slow features with reservoir networks for biologically-inspired robot localization [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: This work proposes a hierarchical biologically- inspired architecture for learning sensor-based spatial represen- tations of a robot environment in an unsupervised way. The learning is based on the fact that high-level concepts, such as the robot position, which vary in a slower timescale, can be found in a fast-varying input signal, like distance sensors. It is also assumed that the input is low-dimensional, providing limited information from the environment. The proposed architecture is composed of three layers, where the first layer, called the reservoir, is a fixed randomly generated recurrent neural network, which projects the input into a high-dimensional, dynamic space. The second layer is trained with Slow Feature Analysis (SFA), generating instantaneous slowly-varying signals from the reservoir states. Using Independent Component Analysis (ICA), the third layer implements sparse coding on the SFA output. The architecture, called RC-SFA, benefits from the short-term memory of the reservoir and the unsupervised learning mechanisms of SFA and ICA. We show that, using a limited number of noisy short-range distance sensors, mobile robots are able to learn to self-localize in simulation as well as in real environments. It is not only the current sensor reading which is needed for predicting the robot position, but also a history of the input stream. We compare the RC-SFA model with a time-delayed model using only SFA and ICA, and show that the reservoir is essential for the temporal processing of the the input stream. Results also show that the SFA and ICA layers show activation patterns which resemble, respectively, the firing of grid cells and hippocampal place cells found in the brain of rodents.
BibTeX: @misc{AntoneloSchrauwen-2010, author = {Antonelo, Eric and Schrauwen, Benjamin}, title = {Learning slow features with reservoir networks for biologically-inspired robot localization}, year = {2010}, url2 = {https://pdfs.semanticscholar.org/cde9/a21dea103a41c23e4bc9e6a8e84b251c97d0.pdf} }
Antonelo, E. & Schrauwen, B.	2012	Learning slow features with reservoir computing for biologically-inspired robot localization [Abstract] [BibTeX] [URL]	Neural Networks , 25(1), 178-190. Publ. Elsevier BV.	article
Abstract: This work proposes a hierarchical biologically-inspired architecture for learning sensor-based spatial representations of a robot environment in an unsupervised way. The first layer is comprised of a fixed randomly generated recurrent neural network, the reservoir, which projects the input into a high-dimensional, dynamic space. The second layer learns instantaneous slowly-varying signals from the reservoir states using Slow Feature Analysis (SFA), whereas the third layer learns a sparse coding on the SFA layer using Independent Component Analysis (ICA). While the SFA layer generates non-localized activations in space, the ICA layer presents high place selectivity, forming a localized spatial activation, characteristic of place cells found in the hippocampus area of the rodent's brain. We show that, using a limited number of noisy short-range distance sensors as input, the proposed system learns a spatial representation of the environment which can be used to predict the actual location of simulated and real robots, without the use of odometry. The results confirm that the reservoir layer is essential for learning spatial representations from low-dimensional input such as distance sensors. The main reason is that the reservoir state reflects the recent history of the input stream. Thus, this fading memory is essential for detecting locations, mainly when locations are ambiguous and characterized by similar sensor readings.
BibTeX: @article{AntoneloSchrauwen-2012, author = {Eric Antonelo and Benjamin Schrauwen}, title = {Learning slow features with reservoir computing for biologically-inspired robot localization}, journal = {Neural Networks}, publisher = {Elsevier {BV}}, year = {2012}, volume = {25}, number = {1}, pages = {178--190}, url = {http://www.sciencedirect.com/science/article/pii/S089360801100222X}, doi = {http://doi.org/10.1016/j.neunet.2011.08.004} }
Antonelo, E.; Schrauwen, B. & Stroobandt, D.	2008	Reservoir computing and slow feature analysis for autonomous map learning and self-localization of small mobile robots [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Small mobile robots must be able to self-localize in their environment in order to accomplish tasks. Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal’s environment). This work seeks to model these place cells by employing three (biologically plau- sible) techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and Independent Component Analysis (ICA). The proposed architecture is composed of three layers, where the bottom layer is a dynamic reservoir of recurrent nodes with fixed weights. The upper layers (SFA and ICA) provides a self- organized formation of place cells, learned in a unsupervised way. Experiments show that a simulated mobile robot with 17 noisy short-range distance sensors is able to self-localize in its environment with the proposed architecture, forming a spatial representation which is dependent on the robot direction.
BibTeX: @misc{AntoneloSchrauwenEtAl-2008, author = {Antonelo, Eric and Schrauwen, Benjamin and Stroobandt, Dirk}, title = {Reservoir computing and slow feature analysis for autonomous map learning and self-localization of small mobile robots}, year = {2008}, url2 = {http://snn.elis.ugent.be/sites/snn/files/icra2009_eric.pdf} }
Ar, I. & Akgul, Y.S.	2013	Action recognition using random forest prediction with combined pose-based and motion-based features [Abstract] [BibTeX] [URL] [URL(2)]	2013 8^th International Conference on Electrical and Electronics Engineering (ELECO) , 315-319. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: In this paper, we propose a novel human action recognition system that uses random forest prediction with statistically combined pose-based and motion-based features. Given a set of training and test image sequences (videos), we first adopt recent techniques that extract low-level features: motion and pose features. Motion-based features which represent motion patterns in the consecutive images, are formed by 3D Haar-like features. Pose-based features are obtained by the calculation of scale invariant contour-based features. Then using statistical methods, we combine these low-level features to a novel compact representation which describes the global motion and the global pose information in the whole image sequence. Finally, Random Forest classification is employed to recognize actions in the test sequences by using this novel representation. Our experimental results on KTH and Weizmann datasets have shown that the combination of pose-based and motion-based features increased the system recognition accuracy. The proposed system also achieved classification rates comparable to the state-of-the-art approaches.
BibTeX: @inproceedings{ArAkgul-2013, author = {Ar, Ilktan and Akgul, Yusuf Sinan}, title = {Action recognition using random forest prediction with combined pose-based and motion-based features}, booktitle = {2013 8\textsuperscript{th} International Conference on Electrical and Electronics Engineering ({ELECO})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2013}, pages = {315--319}, url = {http://ieeexplore.ieee.org/document/6713852/}, url2 = {https://www.researchgate.net/profile/Ilktan_Ar/publication/261423172_Action_recognition_using_random_forest_prediction_with_combined_pose-based_and_motion-based_features/links/00b7d5341188ca0e5d000000.pdf}, doi = {http://doi.org/10.1109/eleco.2013.6713852} }
Aung, T. & Sein, M.M.	2016	Analysing the effect of disaster [Abstract] [BibTeX] [URL]	International Conference on Genetic and Evolutionary Computing , 238-246.	inproceedings
Abstract: Analysing the damage area is the critical task for recovery and reconstruction for the urban area after the disaster. The purposed method is developed to detect the damage areas after the disaster using the satellite images. Most countries are exposed to a number of natural hazards such as Tsunami, Cyclone and landslide. It needs to estimate the destroying areas using the change detection techniques. In this approach, the pre and post satellite images are used to detect the damage areas. The main focus of the paper is to develop an approach that estimates the destroying areas combining the Morphological Building Index (MBI) and Slow Feature Analysis (SFA). He system output the Tchange map for the damage area. The results indicate that the proposed approach is encouraging for automatic detection of damaged buildings and it is a time saving method for monitoring buildings after the disaster happened.
BibTeX: @inproceedings{AungSein-2016, author = {Aung, Thida and Sein, Myint Myint}, title = {Analysing the effect of disaster}, booktitle = {International Conference on Genetic and Evolutionary Computing}, year = {2016}, pages = {238--246}, url = {http://link.springer.com/chapter/10.1007/978-3-319-48490-7_28}, doi = {http://doi.org/10.1007/978-3-319-48490-7_28} }
Bellec, G.; Galtier, M.; Brette, R. & Yger, P.	2016	Slow feature analysis with spiking neurons and its application to audio stimuli [Abstract] [BibTeX] [URL]	Journal of computational neuroscience , 40(3), 317-329. Publ. Springer.	article
Abstract: Extracting invariant features in an unsupervised manner is crucial to perform complex computation such as object recognition, analyzing music or understanding speech. While various algorithms have been proposed to perform such a task, Slow Feature Analysis (SFA) uses time as a means of detecting those invariants, extracting the slowly time-varying components in the input signals. In this work, we address the question of how such an algorithm can be implemented by neurons, and apply it in the context of audio stimuli. We propose a projected gradient implementation of SFA that can be adapted to a Hebbian like learning rule dealing with biologically plausible neuron models. Furthermore, we show that a Spike-Timing Dependent Plasticity learning rule, shaped as a smoothed second derivative, implements SFA for spiking neurons. The theory is supported by numerical simulations, and to illustrate a simple use of SFA, we have applied it to auditory signals. We show that a single SFA neuron can learn to extract the tempo in sound recordings.
BibTeX: @article{BellecGaltierEtAl-2016, author = {Bellec, Guillaume and Galtier, Mathieu and Brette, Romain and Yger, Pierre}, title = {Slow feature analysis with spiking neurons and its application to audio stimuli}, journal = {Journal of computational neuroscience}, publisher = {Springer}, year = {2016}, volume = {40}, number = {3}, pages = {317--329}, url = {http://link.springer.com/content/pdf/10.1007/s10827-016-0599-3.pdf}, doi = {http://doi.org/10.1007/s10827-016-0599-3} }
Bengio, Y.; Courville, A. & Vincent, P.	2013	Representation learning: a review and new perspectives [Abstract] [BibTeX] [URL(2)]	IEEE transactions on pattern analysis and machine intelligence , 35(8), 1798-1828. Publ. IEEE.	article
Abstract: The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different ex- planatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implement- ing such priors. This paper reviews recent work in the area of unsu- pervised feature learning and joint training of deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep architectures. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connec- tions between representation learning, density estimation and manifold learning.
BibTeX: @article{BengioCourvilleEtAl-2013, author = {Bengio, Yoshua and Courville, Aaron and Vincent, Pascal}, title = {Representation learning: a review and new perspectives}, journal = {IEEE transactions on pattern analysis and machine intelligence}, publisher = {IEEE}, year = {2013}, volume = {35}, number = {8}, pages = {1798--1828}, url2 = {http://mlsurveys.s3.amazonaws.com/110.pdf} }
Bergstra, J.	2011	Incorporating complex cells into neural networks for pattern classification [Abstract] [BibTeX] [URL]	Département d'informatique et de recherche opérationnelle Faculté des arts et des sciences, Université de Montréa, Département d'informatique et de recherche opérationnelle Faculté des arts et des sciences, Université de Montréa .	phdthesis
Abstract: Computational neuroscientists have hypothesized that the visual system from the retina to at least primary visual cortex is continuously tting a latent variable probability model to its stream of perceptions. It is not known exactly which probability model, nor exactly how the tting takes place, but known algorithms for fitting such models require conditional estimates of the latent variables. This gives us a strong hint as to why the visual system might be tting such a model; in the right kind of model those conditional estimates can also serve as excellent features for analyzing the semantic content of images perceived. The work presented here uses image classi cation performance (accurate discrimination between common classes of objects) as a basis for comparing visual system models, and algorithms for tting those models as probability densities to images. This dissertation (a) finds that models based on visual area V1's complex cells generalize better from labeled training examples than conventional neural networks whose hidden units are more like V1's simple cells, (b) presents novel interpretations for complex-cell- based visual system models as probability distributions and novel algorithms for tting them to data, and (c) demonstrates that these models form better features for image classi cation after they are rst trained as probability models. Visual system models based on complex cells achieve some of the best results to date on the CIFAR-10 image classi cation benchmark, and samples from their probability distributions indicate that they have learnt to capture important aspects of natural images. Two auxiliary technical innovations that made this work possible are also de- scribed: a random search algorithm for selecting hyper-parameters, and an opti- mizing compiler for matrix-valued mathematical expressions which can target both CPU and GPU devices.
BibTeX: @phdthesis{Bergstra-2011, author = {Bergstra, James}, title = {Incorporating complex cells into neural networks for pattern classification}, school = {D{\'{e}}partement d'informatique et de recherche op{\'{e}}rationnelle Facult{\'{e}} des arts et des sciences, Universit{\'{e}} de Montr{\'{e}}a}, year = {2011}, url = {http://www-etud.iro.umontreal.ca/~bergstrj/publications/11_These.pdf} }
Bergstra, J.S. & Bengio, Y.	2009	Slow, decorrelated features for pretraining complex cell-like networks [BibTeX]	Advances in neural information processing systems , 99-107.	inproceedings
BibTeX: @inproceedings{BergstraBengio-2009, author = {Bergstra, James S and Bengio, Yoshua}, title = {Slow, decorrelated features for pretraining complex cell-like networks}, booktitle = {Advances in neural information processing systems}, year = {2009}, pages = {99--107} }
Berkes, P.	2005	Pattern recognition with slow feature analysis. [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 4104.	misc
BibTeX: @misc{Berkes-2005a, author = {Pietro Berkes}, title = {Pattern recognition with slow feature analysis.}, year = {2005}, volume = {4104}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/4104/} }
Berkes, P.	2005	Temporal slowness as an unsupervised learning principle: self-organization of complex-cell receptive fields and application to pattern recognition. [BibTeX]	PhD thesis, Institute for Biology, Humboldt University Berlin, D-10099 Berlin, Germany .	phdthesis
BibTeX: @phdthesis{Berkes-2005c, author = {Pietro Berkes}, title = {Temporal slowness as an unsupervised learning principle: self-organization of complex-cell receptive fields and application to pattern recognition.}, school = {Institute for Biology}, year = {2005} }
Berkes, P. & Wiskott, L.	2002	Applying slow feature analysis to image sequences yields a rich repertoire of complex cell properties. [Abstract] [BibTeX] [URL] [URL(2)]	Proc. Intl. Conf. on Artificial Neural Networks (ICANN'02) , Lecture Notes in Computer Science , 81-86. Ed. José & Dorronsoro, R. Publ. Springer.	inproceedings
Abstract: We apply Slow Feature Analysis (SFA) to image sequences generated from natural images using a range of spatial transformations. An analysis of the resulting receptive fields shows that they have a rich spectrum of invariances and share many properties with complex and hypercomplex cells of the primary visual cortex. Furthermore, the dependence of the solutions on the statistics of the transformations is investigated.
BibTeX: @inproceedings{BerkesWiskott-2002, author = {Pietro Berkes and Laurenz Wiskott}, title = {Applying slow feature analysis to image sequences yields a rich repertoire of complex cell properties.}, booktitle = {Proc.\ Intl.\ Conf.\ on Artificial Neural Networks (ICANN'02)}, publisher = {Springer}, year = {2002}, pages = {81--86}, url = {http://link.springer.com/chapter/10.1007/3-540-46084-5_14}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/BerkesWiskott-2002-ProcICANN-SFAComplexCells-Preprint.pdf}, doi = {http://doi.org/10.1007/3-540-46084-5_14} }
Berkes, P. & Wiskott, L.	2003	Slow feature analysis yields a rich repertoire of complex-cells properties. [BibTeX]	Proc. 29^th Göttingen Neurobiology Conference, Göttingen, Germany , 602-603. Eds. Elsner, N. & Zimmermann, H. Publ. Georg Thieme Verlag, Stuttgart.	inproceedings
BibTeX: @inproceedings{BerkesWiskott-2003b, author = {Pietro Berkes and Laurenz Wiskott}, title = {Slow feature analysis yields a rich repertoire of complex-cells properties.}, booktitle = {Proc.\ 29\textsuperscript{th} G{\"o}ttingen Neurobiology Conference, G\"ottingen, Germany}, publisher = {Georg Thieme Verlag}, year = {2003}, pages = {602--603} }
Berkes, P. & Wiskott, L.	2003	Slow feature analysis yields a rich repertoire of complex-cell properties. [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 2804.	misc
BibTeX: @misc{BerkesWiskott-2003a, author = {Pietro Berkes and Laurenz Wiskott}, title = {Slow feature analysis yields a rich repertoire of complex-cell properties.}, year = {2003}, volume = {2804}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/2804/} }
Berkes, P. & Wiskott, L.	2004	Slow feature analysis yields a rich repertoire of complex-cells properties. [BibTeX]	Proc. Early Cognitive Vision Workshop, May 28 - Jun 1, Isle Of Skye, Scotland .	inproceedings
BibTeX: @inproceedings{BerkesWiskott-2004, author = {Pietro Berkes and Laurenz Wiskott}, title = {Slow feature analysis yields a rich repertoire of complex-cells properties.}, booktitle = {Proc.\ Early Cognitive Vision Workshop, May 28 -- Jun 1, Isle Of Skye, Scotland}, year = {2004} }
Berkes, P. & Wiskott, L.	2005	Slow feature analysis yields a rich repertoire of complex cell properties. [Abstract] [BibTeX] [URL] [URL(2)]	Journal of Vision , 5(6), 579-602.	article
Abstract: In this study, we investigate temporal slowness as a learning principle for receptive fields using slow feature analysis, a new algorithm to determine functions that extract slowly varying signals from the input data. We find a good qualitative and quantitative match between the set of learned functions trained on image sequences and the population of complex cells in the primary visual cortex (V1). The functions show many properties found also experimentally in complex cells, such as direction selectivity, non-orthogonal inhibition, end-inhibition, and side-inhibition. Our results demonstrate that a single unsupervised learning principle can account for such a rich repertoire of receptive field properties.
BibTeX: @article{BerkesWiskott-2005c, author = {Pietro Berkes and Laurenz Wiskott}, title = {Slow feature analysis yields a rich repertoire of complex cell properties.}, journal = {Journal of Vision}, year = {2005}, volume = {5}, number = {6}, pages = {579--602}, url = {http://journalofvision.org/5/6/9/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/BerkesWiskott-2005c-JoV-SFAComplexCells.pdf}, doi = {http://doi.org/10.1167/5.6.9} }
Bertram, D.	2012	Untersuchungen zur Varianzreduktion beschleunigungsbasierter 3D-Gestendaten [Abstract] [BibTeX] [URL(2)]	Master thesis, Faculty of Computer Science and Engineering Science, Cologne University of Applied Science, Master thesis, Faculty of Computer Science and Engineering Science, Cologne University of Applied Science .	mastersthesis
Abstract: Verschiedene Arbeiten haben sich bereits mit der Klassifikation von 3D-Gestendaten beschäftigt, wobei die Varianz aller verwendeten Verfahren zwei Gemeinsamkeiten be- sitzt. Keine der Arbeiten erzielt benutzerunabhängig ähnlich gute Ergebnisse wie im benutzerabhängigen Fall und keine Arbeit erzielt eine 100% Erkennung. Diese Arbeit untersuchte am Beispiel einer Gestenerkennung mittels Slow Feature Analysis (SFA), die auf einem iPhone umgesetzt wurde, welche Unterschiede zwischen benutzerabhängiger und benutzerunabhängiger Erkennung bestimmbar sind und wie sich diese in ihrer Varianz reduzieren lassen. Für die Betrachtungen wurden zwei personendisjunkte Datensätze verwendet. Es wurden verschiedene Einflüsse bestimmt und durch Operatoren zur Invarianz überführt. Durch die bestimmten Operatoren ist es möglich, die Erkennungswahrscheinlichkeit im benutzerabhängigen und im benutzerunabhängigen Fall zu steigern. Es wurden drei Invarianzen erschaffen, die Rotationsinvarianz durch eine Datensatzrotation mittels Quaternionen, die Gestensegmentierung durch Ruheauslöschung sowie dem Ausklingen um Bewegungsab- brüche zu kompensieren. Die SFA hat sich als robustes und zuverlässiges Verfahren erwiesen, welches durch seine Analyseeigenschaften sogar für rotierte Gesten korrekt klassifizierbare Eigenschaftsvektoren bestimmt. Durch die unterschiedlichen Methoden wurde die Erkennungswahr- scheinlichkeit im benutzerunabhängigen Fall gesteigert und durch die Überführung von Einflussfaktoren zur Invarianz die Benutzbarkeit für einen ”untrainierten“ Benutzer deutlich erhöht. Weiterhin wurde festgestellt, dass die Betrachtung der Datensatze im Bild- und Frequenzbereich zu unterschiedlichen Fehlerkennungen führen, diese somit unterschiedliche Informationen für die SFA besitzen.
BibTeX: @mastersthesis{Bertram-2012, author = {Bertram, Daniel}, title = {Untersuchungen zur {V}arianzreduktion beschleunigungsbasierter {3D-G}estendaten}, school = {Master thesis, Faculty of Computer Science and Engineering Science, Cologne University of Applied Science}, year = {2012}, url2 = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/MT-Bertram_final-2012.pdf} }
Bethge, M.; Gerwinn, S. & Macke, J.H.	2007	Unsupervised learning of a steerable basis for invariant image representations [Abstract] [BibTeX] [URL] [URL(2)]	Electronic Imaging 2007 , 64920C-64920C.	inproceedings
Abstract: There are two aspects to unsupervised learning of invariant representations of images: First, we can reduce the dimensionality of the representation by finding an optimal trade-off between temporal stability and informa- tiveness. We show that the answer to this optimization problem is generally not unique so that there is still considerable freedom in choosing a suitable basis. Which of the many optimal representations should be selected? Here, we focus on this second aspect, and seek to find representations that are invariant under geometrical trans- formations occuring in sequences of natural images. We utilize ideas of ‘steerability’ and Lie groups, which have been developed in the context of filter design. In particular, we show how an anti-symmetric version of canonical correlation analysis can be used to learn a full-rank image basis which is steerable with respect to rotations. We provide a geometric interpretation of this algorithm by showing that it finds the two-dimensional eigensubspaces of the average bivector. For data which exhibits a variety of transformations, we develop a bivector clustering algorithm, which we use to learn a basis of generalized quadrature pairs (i.e. ‘complex cells’) from sequences of natural images.
BibTeX: @inproceedings{BethgeGerwinnEtAl-2007, author = {Bethge, Matthias and Gerwinn, Sebastian and Macke, Jakob H}, title = {Unsupervised learning of a steerable basis for invariant image representations}, booktitle = {Electronic Imaging 2007}, year = {2007}, pages = {64920C--64920C}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1298483}, url2 = {https://www.researchgate.net/profile/Matthias_Bethge/publication/41781729_Unsupervised_learning_of_a_steerable_basis_for_invariant_image_representations/links/0fcfd509bdb291078a000000.pdf}, doi = {http://doi.org/10.1117/12.711119} }
Blaschke, T.	2005	Independent component analysis and slow feature analysis: relations and combination. [Abstract] [BibTeX] [URL] [URL(2)]	PhD thesis, Institute for Physics, Humboldt University Berlin, D-10099 Berlin, Germany .	phdthesis
Abstract: Within this thesis, we focus on the relation between independent component analysis (ICA) and slow feature analysis (SFA). To allow a comparison between both methods we introduce CuBICA2, an ICA algorithm based on second-order statistics only, i.e. cross-correlations. In contrast to algorithms based on higher-order statistics not only instantaneous cross-correlations but also time-delayed cross correlations are considered for minimization. CuBICA2 requires signal components with auto-correlation like in SFA, and has the ability to separate source signal components that have a Gaussian distribution. Furthermore, we derive an alternative formulation of the SFA objective function and compare it with that of CuBICA2. In the case of a linear mixture the two methods are equivalent if a single time delay is taken into account. The comparison can not be extended to the case of several time delays. For ICA a straightforward extension can be derived, but a similar extension to SFA yields an objective function that can not be interpreted in the sense of SFA. However, a useful extension in the sense of SFA to more than one time delay can be derived. This extended SFA reveals the close connection between the slowness objective of SFA and temporal predictability. Furthermore, we combine CuBICA2 and SFA. The result can be interpreted from two perspectives. From the ICA point of view the combination leads to an algorithm that solves the nonlinear blind source separation problem. From the SFA point of view the combination of ICA and SFA is an extension to SFA in terms of statistical independence. Standard SFA extracts slowly varying signal components that are uncorrelated meaning they are statistically independent up to second-order. The integration of ICA leads to signal components that are more or less statistically independent.
BibTeX: @phdthesis{Blaschke-2005, author = {Tobias Blaschke}, title = {Independent component analysis and slow feature analysis: relations and combination.}, school = {Institute for Physics}, year = {2005}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?lang=ger&id=25458}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Blaschke-2005-Dissertation.pdf} }
Blaschke, T.; Berkes, P. & Wiskott, L.	2006	What is the relationship between slow feature analysis and independent component analysis? [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 18(10), 2495-2508.	article
Abstract: We present an analytical comparison between linear slow feature analysis and second-order independent component analysis, and show that in the case of one time delay the two approaches are equivalent. We also consider the case of several time delays and discuss two possible extensions of slow feature analysis.
BibTeX: @article{BlaschkeBerkesEtAl-2006, author = {T. Blaschke and P. Berkes and L. Wiskott}, title = {What is the relationship between slow feature analysis and independent component analysis?}, journal = {Neural Computation}, year = {2006}, volume = {18}, number = {10}, pages = {2495--2508}, url = {http://www.mitpressjournals.org/doi/10.1162/neco.2006.18.10.2495}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/BlaschkeBerkesEtAl-2006-NeurComp-SFAvsICA.pdf}, doi = {http://doi.org/10.1162/neco.2006.18.10.2495} }
Blaschke, T. & Wiskott, L.	2005	Nonlinear blind source separation by integrating independent component analysis and slow feature analysis. [BibTeX]	Proc. Advances in Neural Information Processing Systems 17 (NIPS'04) , 177-184. Eds. Saul, L. K.; Weiss, Y.; Lé & on Bottou Publ. The MIT Press.	inproceedings
BibTeX: @inproceedings{BlaschkeWiskott-2005, author = {T. Blaschke and L. Wiskott}, title = {Nonlinear blind source separation by integrating independent component analysis and slow feature analysis.}, booktitle = {Proc.\ Advances in Neural Information Processing Systems 17 (NIPS'04)}, publisher = {The MIT Press}, year = {2005}, pages = {177--184} }
Blaschke, T. & Wiskott, L.	2004	Independent slow feature analysis and nonlinear blind source separation. [Abstract] [BibTeX] [URL] [URL(2)]	Proc. of the 5^th Int. Conf. on Independent Component Analysis and Blind Signal Separation (ICA'04), Granada, Spain , Lecture Notes in Computer Science . Publ. Springer.	inproceedings
Abstract: We present independent slow feature analysis as a new method for nonlinear blind source separation. It circumvents the indeterminacy of nonlinear independent component analysis by combining the objectives of statistical independence and temporal slowness. The principle of temporal slowness is adopted from slow feature analysis, an unsupervised method to extract slowly varying features from a given observed vectorial signal. The performance of the algorithm is demonstrated on nonlinearly mixed speech data.
BibTeX: @inproceedings{BlaschkeWiskott-2004b, author = {T. Blaschke and L. Wiskott}, title = {Independent slow feature analysis and nonlinear blind source separation.}, booktitle = {Proc. of the 5\textsuperscript{th} Int. Conf. on Independent Component Analysis and Blind Signal Separation (ICA'04), Granada, Spain}, publisher = {Springer}, year = {2004}, url = {http://link.springer.com/chapter/10.1007/978-3-540-30110-3_94}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/BlaschkeWiskott-2004b-ProcICA-ISFA-Preprint.pdf}, doi = {http://doi.org/10.1007/978-3-540-30110-3_94} }
Blaschke, T.; Zito, T. & Wiskott, L.	2007	Independent slow feature analysis and nonlinear blind source separation. [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 19(4), 994-1021.	article
Abstract: In the linear case statistical independence is a sufficient criterion for performing blind source separation. In the nonlinear case, however, it leaves an ambiguity in the solutions that has to be resolved by additional criteria. Here we argue that temporal slowness complements statistical independence well and that a combination of the two leads to unique solutions of the nonlinear blind source separation problem. The algorithm we present is a combination of second-order Independent Component Analysis and Slow Feature Analysis and is referred to as Independent Slow Feature Analysis. Its performance is demonstrated on nonlinearly mixed music data. We conclude that slowness is indeed a useful complement to statistical independence but that time-delayed second-order moments are only a weak measure of statistical independence.
BibTeX: @article{BlaschkeZitoEtAl-2007, author = {Tobias Blaschke and Tiziano Zito and Laurenz Wiskott}, title = {Independent slow feature analysis and nonlinear blind source separation.}, journal = {Neural Computation}, year = {2007}, volume = {19}, number = {4}, pages = {994--1021}, url = {http://neco.mitpress.org/cgi/content/abstract/19/4/994}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/BlaschkeZitoEtAl-2007-NeurComp-ISFA.pdf}, doi = {http://doi.org/10.1162/neco.2007.19.4.994} }
Böhmer, W.	2012	Robot navigation using reinforcement learning and slow feature analysis [Abstract] [BibTeX] [URL(2)]	Technische Universität Berlin, Fakultät für Elektrotechnik und Informatik, Technische Universität Berlin, Fakultät für Elektrotechnik und Informatik e-print arXiv:1205.0986 .	mastersthesis
Abstract: The application of reinforcement learning algorithms onto real life problems always bears the challenge of filtering the environmental state out of raw sensor readings. While most approaches use heuristics, biology suggests that there must exist an unsupervised method to construct such filters automatically. Besides the extraction of environmental states, the filters have to represent them in a fashion that support modern reinforcement algorithms. Many popular algorithms use a linear architecture, so one should aim at filters that have good approximation properties in combination with linear functions. This thesis wants to propose the unsupervised method slow feature analysis (SFA) for this task. Presented with a random sequence of sensorreadings, SFA learns a set of filters. With growing model complexity and training examples, the filters converge against trigonometric polynomial functions. These are known to possess excellent approximation capabilities and should therfore support the reinforcement algorithms well. We evaluate this claim on a robot. The task is to learn a navigational control in a simple environment using the least square policy iteration (LSPI) algorithm. The only accessible sensor is a head mounted video camera, but without meaningful filtering, video images are not suited as LSPI input. We will show that filters learned by SFA, based on a random walk video of the robot, allow the learned control to navigate successfully in ca. 80% of the test trials.
BibTeX: @mastersthesis{Boehmer-2012, author = {Wendelin B{\"{o}}hmer}, title = {Robot navigation using reinforcement learning and slow feature analysis}, school = {Technische Universit{\"{a}}t Berlin, Fakult{\"{a}}t f{\"{u}}r Elektrotechnik und Informatik}, year = {2012}, howpublished = {e-print arXiv:1205.0986}, url2 = {https://pdfs.semanticscholar.org/75e5/278d2fc2259dee117edf2aef48189ee1ed68.pdf} }
Böhmer, W.	2017	Representation and generalization in autonomous reinforcement learning [BibTeX] [URL]	Technische Universität Berlin, Technische Universität Berlin .	phdthesis
BibTeX: @phdthesis{Boehmer-2017, author = {Wendelin B\"ohmer}, title = {Representation and generalization in autonomous reinforcement learning}, school = {Technische Universit\"at Berlin}, year = {2017}, url = {https://depositonce.tu-berlin.de/handle/11303/6150}, doi = {http://doi.org/10.14279/depositonce-5715} }
Böhmer, W.; Grünewälder, S.; Nickisch, H. & Obermayer, K.	2011	Regularized sparse kernel slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	Joint European Conference on Machine Learning and Knowledge Discovery in Databases , 235-248. Publ. Springer Nature.	inproceedings
Abstract: This paper develops a kernelized slow feature analysis (SFA) algorithm. SFA is an unsupervised learning method to extract features which encode latent variables from time series. Generative relationships are usually complex, and current algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to provide a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small but complex data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. Versatility and performance of our method are demonstrated on audio and video data sets.
BibTeX: @inproceedings{BoehmerGruenewaelderEtAl-2011, author = {B{\"o}hmer, Wendelin and Gr{\"u}new{\"a}lder, Steffen and Nickisch, Hannes and Obermayer, Klaus}, title = {Regularized sparse kernel slow feature analysis}, booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, publisher = {Springer Nature}, year = {2011}, pages = {235--248}, url = {http://link.springer.com/chapter/10.1007/978-3-642-23780-5_25}, url2 = {http://hannes.nickisch.org/papers/conferences/boehmer11regSKSFA.pdf}, doi = {http://doi.org/10.1007/978-3-642-23780-5_25} }
Böhmer, W.; Grünewälder, S.; Nickisch, H. & Obermayer, K.	2012	Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis [Abstract] [BibTeX] [URL]	Machine Learning , 89(1-2), 67-86. Publ. Springer US.	article
Abstract: Without non-linear basis functions many problems can not be solved by linear algorithms. This article proposes a method to automatically construct such basis functions with slow feature analysis (SFA). Non-linear optimization of this unsupervised learning method generates an orthogonal basis on the unknown latent space for a given time series. In contrast to methods like PCA, SFA is thus well suited for techniques that make direct use of the latent space. Real-world time series can be complex, and current SFA algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to develop a kernelized SFA algorithm which provides a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. We hypothesize that our algorithm generates a feature space that resembles a Fourier basis in the unknown space of latent variables underlying a given real-world time series. We evaluate this hypothesis at the example of a vowel classification task in comparison to sparse kernel PCA. Our results show excellent classification accuracy and demonstrate the superiority of kernel SFA over kernel PCA in encoding latent variables.
BibTeX: @article{BoehmerGruenewaelderEtAl-2012, author = {B{\"o}hmer, Wendelin and Gr{\"u}new{\"a}lder, Steffen and Nickisch, Hannes and Obermayer, Klaus}, title = {Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis}, journal = {Machine Learning}, publisher = {Springer US}, year = {2012}, volume = {89}, number = {1-2}, pages = {67--86}, url = {http://link.springer.com/article/10.1007/s10994-012-5300-0}, doi = {http://doi.org/10.1007/s10994-012-5300-0} }
Böhmer, W.; Grünewälder, S. & Obermayer, K.	2009	State extraction by dimensionality reduction [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Real world data (e.g. video images) are usually high dimensional and present information highly mixed and noise afflicted. Most applications therefore require a dimensionality reduction or information filtering beforehand. Such filters have to present the desired information in an applicable fashion and have to make sure few are lost. Several methods exist that learn these filters from the statistics of presented training data (e.g. PCA, CCA, PLS or SFA [1]). We used the unsupervised method of slow feature analysis (SFA) to extract the position of a robot from the images of its head-mounted camera. SFA assumes a hidden low dimensional state x that changes slowly over time (in our case the position of a camera). The observed data (images recorded by this camera) is generated by an unknown bijective render function f(x). Given unlimited training data and a non restricted function class, one can derive the output of the optimal filter for some representative cases analytically. For these cases it has been proven that the optimal outputs are trigonometric basis functions in the domain of x [2]. This result is independent of the render function f(x), which is effectively inverted by the learned filter. To catch the non linear correlations in video images, we constructed a kernelized SFA algorithm analogous to kernel PCA [3], which outperformed its linear counterpart considerably. In order to deal with the huge number of training samples needed to catch the statistics of real images, we employed a sparse kernel matrix approximation method first introduced by Csat ́o and Opper [4]. The resulting feature space (an approximation of the space of trigonometric polynomials) is particularly well suited to approximate continuous functions with a linear model, e.g. value functions in reinforcement learning. We demonstrated this by learning the robots control in a simple navigation task. However, trigonometric polynomials are global functions and therefore the filters need support on their complete domain. In light of the huge computational demand one would rather like to extract the robots position in a sparse feature space that consists of localized basis functions, e.g. Gaussian bells. These are only active in a small region of their domain and therefore can be individually expressed by a sparse kernel expansion, i.e. with a small number of support vectors. In future works, we plan to construct optimization problems based on sparseness techniques that produce such basis functions and use convex optimization algorithms to solve them [5].
BibTeX: @misc{BoehmerGruenewaelderEtAl-2009, author = {B{\"o}hmer, Wendelin and Gr{\"u}new{\"a}lder, Steffen and Obermayer, Klaus}, title = {State extraction by dimensionality reduction}, year = {2009}, url2 = {https://www.researchgate.net/profile/Wendelin_Boehmer/publication/267799911_State_Extraction_by_Dimensionality_Reduction/links/54cb68360cf2240c27e7d56b.pdf} }
Böhmer, W.; Grünewälder, S.; Shen, Y.; Musial, M. & Obermayer, K.	2013	Construction of approximation spaces for reinforcement learning. [Abstract] [BibTeX] [URL(2)]	Journal of Machine Learning Research , 14(1), 2067-2118.	article
Abstract: Linear reinforcement learning (RL) algorithms like least-squares temporal difference learning (LSTD) require basis functions that span approximation spaces of potential value functions. This article investigates methods to construct these bases from samples. We hypothesize that an ideal approximation spaces should encode diffusion distances and that slow feature analysis (SFA) constructs such spaces. To validate our hypothesis we provide theoretical statements about the LSTD value approximation error and induced metric of approximation spaces constructed by SFA and the state-of-the-art methods Krylov bases and proto-value functions (PVF). In particular, we prove that SFA minimizes the average (over all tasks in the same environment) bound on the above approx- imation error. Compared to other methods, SFA is very sensitive to sampling and can sometimes fail to encode the whole state space. We derive a novel importance sampling modification to compensate for this effect. Finally, the LSTD and least squares policy iteration (LSPI) performance of approximation spaces constructed by Krylov bases, PVF, SFA and PCA is compared in benchmark tasks and a visual robot navigation experiment (both in a realistic simulation and with a robot). The results support our hypothesis and suggest that (i) SFA provides subspace-invariant features for MDPs with self-adjoint transition operators, which allows strong guarantees on the approximation error, (ii) the modified SFA algorithm is best suited for LSPI in both discrete and continuous state spaces and (iii) approximation spaces encoding diffusion distances facilitate LSPI performance.
BibTeX: @article{BoehmerGruenewaelderEtAl-2013, author = {B{\"o}hmer, Wendelin and Gr{\"u}new{\"a}lder, Steffen and Shen, Yun and Musial, Marek and Obermayer, Klaus}, title = {Construction of approximation spaces for reinforcement learning.}, journal = {Journal of Machine Learning Research}, year = {2013}, volume = {14}, number = {1}, pages = {2067--2118}, url2 = {https://pdfs.semanticscholar.org/fc2f/fb9daf9f0dd07e755d7ad5633907efb0a4b7.pdf} }
Böhmer, W.; Guo, R. & Obermayer, K.	2016	Non-deterministic policy improvement stabilizes approximated reinforcement learning [Abstract] [BibTeX] [URL]	e-print arXiv:1612.07548 .	misc
Abstract: This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by controlling the improvements’ stochastic- ity. Additionally we show that a suitable representation of the value function also stabilizes the solution to some degree. The presented approach is simple and should also be easily transferable to more sophisticated algorithms like deep reinforcement learning.
BibTeX: @misc{BoehmerGuoEtAl-2016, author = {B{\"{o}}hmer, Wendelin and Guo, Rong and Obermayer, Klaus}, title = {Non-deterministic policy improvement stabilizes approximated reinforcement learning}, year = {2016}, howpublished = {e-print arXiv:1612.07548}, url = {https://arxiv.org/pdf/1612.07548.pdf} }
Böhmer, W.; Springenberg, J.T.; Boedecker, J.; Riedmiller, M. & Obermayer, K.	2015	Autonomous learning of state representations for control: an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations [Abstract] [BibTeX] [URL] [URL(2)]	KI-Künstliche Intelligenz , 29(4), 353-362. Publ. Springer.	article
Abstract: This article reviews an emerging field that aims for autonomous reinforcement learning (RL) directly on sensor-observations. Straightforward end-to-end RL has recently shown remarkable success, but relies on large amounts of samples. As this is not feasible in robotics, we review two approaches to learn intermediate state representations from previous experiences: deep auto-encoders and slow-feature analysis. We analyze theoretical properties of the representations and point to potential improvements.
BibTeX: @article{BoehmerSpringenbergEtAl-2015, author = {B{\"{o}}hmer, Wendelin and Springenberg, Jost Tobias and Boedecker, Joschka and Riedmiller, Martin and Obermayer, Klaus}, title = {Autonomous learning of state representations for control: an emerging field aims to autonomously learn state representations for reinforcement learning agents from their real-world sensor observations}, journal = {KI-K{\"{u}}nstliche Intelligenz}, publisher = {Springer}, year = {2015}, volume = {29}, number = {4}, pages = {353--362}, url = {http://link.springer.com/content/pdf/10.1007/s13218-015-0356-1.pdf}, url2 = {https://pdfs.semanticscholar.org/68e8/7a10b40f6ba5fd2ac8c2262eab0373bd2ed4.pdf}, doi = {http://doi.org/10.1007/s13218-015-0356-1} }
Bray, A. & Martinez, D.	2002	Kernel-based extraction of slow features: complex cells learn disparity and translation invariance from natural images [Abstract] [BibTeX] [URL] [URL(2)]	NIPS. Vol. 15. .	inproceedings
Abstract: In Slow Feature Analysis (SFA [1]), it has been demonstrated that high-order invariant properties can be extracted by projecting inputs into a nonlinear space and computing the slowest changing features in this space; this has been proposed as a simple general model for learning nonlinear invariances in the visual system. However, this method is highly constrained by the curse of dimensionality which limits it to simple theoretical simulations. This paper demonstrates that by using a different but closely-related objective function for extracting slowly varying features ([2, 3]), and then exploiting the kernel trick, this curse can be avoided. Using this new method we show that both the complex cell properties of translation invariance and disparity coding can be learnt simultaneously from natural images when complex cells are driven by simple cells also learnt from the image.
BibTeX: @inproceedings{BrayMartinez-2002, author = {Bray, Alistair and Martinez, Dominique}, title = {Kernel-based extraction of slow features: complex cells learn disparity and translation invariance from natural images}, booktitle = {NIPS. Vol. 15.}, year = {2002}, url = {https://papers.nips.cc/paper/2209-kernel-based-extraction-of-slow-features-complex-cells-learn-disparity-and-translation-invariance-from-natural-images.pdf}, url2 = {https://pdfs.semanticscholar.org/bb25/dcb75cc5c0261d0b1e07cf0231ad1f1524eb.pdf} }
Bray, A. & Martinez, D.	2003	Complex cells learn disparity and translation invariance from natural images [Abstract] [BibTeX]	Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference , 15, 269.	inproceedings
Abstract: In Slow Feature Analysis (SFA [1]), it has been demonstrated that high-order invariant properties can be extracted by projecting in- puts into a nonlinear space and computing the slowest changing features in this space; this has been proposed as a simple general ...
BibTeX: @inproceedings{BrayMartinez-2003, author = {Bray, Alistair and Martinez, Dominique}, title = {Complex cells learn disparity and translation invariance from natural images}, booktitle = {Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference}, year = {2003}, volume = {15}, pages = {269} }
Cai, Y. & Wang, G.	2010	AR parameters-based nonlinear blind source extraction [Abstract] [BibTeX] [URL] [URL(2)]	Applied Mechanics and Materials , 20, 1129-1135.	inproceedings
Abstract: In nonlinear blind source separation (BSS) independence is not sufficient to recover the original source signal and additional criteria are needed to sufficiently constrain the optimization problem. Here we introduce autoregressive (AR) parameters as criteria and combined with expansion space develop a new method, which lead to a unique solution of the nonlinear BSS problem. The proposed method is based on two key assumptions. One lies in that a source signal’s AR parameters can be roughly estimated before operation, and the other is that expansion space, such as kernel feature space, should be chosen rich enough to approximate the nonlinearity. This method can extract the desired source signal as a unique solution with the help of this signal’s AR parameter, or it extracts one signal at one time. Thus it is also referred to as nonlinear blind source extraction (BSE). Its performance is demonstrated on nonlinearly mixed speech data.
BibTeX: @inproceedings{CaiWang-2010, author = {Cai, Ying and Wang, Gang}, title = {{AR} parameters-based nonlinear blind source extraction}, booktitle = {Applied Mechanics and Materials}, year = {2010}, volume = {20}, pages = {1129--1135}, url = {https://www.scientific.net/AMM.20-23.1129.pdf}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.698.850&rep=rep1&type=pdf}, doi = {http://doi.org/10.4028/www.scientific.net/amm.20-23.1129} }
Cao, K.; Bednarz, B.; Smith, L.S.; Foo, T.K.F. & Patwardhan, K.A.	2015	Respiration induced fiducial motion tracking in ultrasound using an extended SFA approach [Abstract] [BibTeX] [URL]	SPIE Medical Imaging , 94190S-94190S.	inproceedings
Abstract: Radiation therapy (RT) plays an essential role in the management of cancers. The precision of the treatment delivery process in chest and abdominal cancers is often impeded by respiration induced tumor positional variations, which are accounted for by using larger therapeutic margins around the tumor volume leading to sub-optimal treatment deliveries and risk to healthy tissue. Real-time tracking of tumor motion during RT will help reduce unnecessary margin area and benefit cancer patients by allowing the treatment volume to closely match the positional variation of the tumor volume over time. In this work, we propose a fast approach which enables transferring the pre-estimated target (e.g. tumor) motion extracted from ultrasound (US) image sequences in training stage (e.g. before RT) to online data in real-time (e.g. acquired during RT). The method is based on extracting feature points of the target object, exploiting low-dimensional description of the feature motion through slow feature analysis, and finding the most similar image frame from training data for estimating current/online object location. The approach is evaluated on two 2D + time and one 3D + time US acquisitions. The locations of six annotated fiducials are used for designing experiments and validating tracking accuracy. The average fiducial distance between expert's annotation and the location extracted from our indexed training frame is 1.9±0.5mm. Adding a fast template matching procedure within a small search range reduces the distance to 1.4±0.4mm. The tracking time per frame is on the order of millisecond, which is below the frame acquisition time. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
BibTeX: @inproceedings{CaoBednarzEtAl-2015, author = {Cao, Kunlin and Bednarz, Bryan and Smith, LS and Foo, Thomas KF and Patwardhan, Kedar A}, title = {Respiration induced fiducial motion tracking in ultrasound using an extended {SFA} approach}, booktitle = {SPIE Medical Imaging}, year = {2015}, pages = {94190S--94190S}, url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2209821}, doi = {http://doi.org/10.1117/12.2082591} }
Carlin, M.A. & Elhilali, M.	2013	Sustained firing of model central auditory neurons yields a discriminative spectro-temporal representation for natural sounds [Abstract] [BibTeX] [URL]	PLOS Comput Biol , 9(3), e1002982. Publ. Public Library of Science.	article
Abstract: The processing characteristics of neurons in the central auditory system are directly shaped by and reflect the statistics of natural acoustic environments, but the principles that govern the relationship between natural sound ensembles and observed responses in neurophysiological studies remain unclear. In particular, accumulating evidence suggests the presence of a code based on sustained neural firing rates, where central auditory neurons exhibit strong, persistent responses to their preferred stimuli. Such a strategy can indicate the presence of ongoing sounds, is involved in parsing complex auditory scenes, and may play a role in matching neural dynamics to varying time scales in acoustic signals. In this paper, we describe a computational framework for exploring the influence of a code based on sustained firing rates on the shape of the spectro-temporal receptive field (STRF), a linear kernel that maps a spectro-temporal acoustic stimulus to the instantaneous firing rate of a central auditory neuron. We demonstrate the emergence of richly structured STRFs that capture the structure of natural sounds over a wide range of timescales, and show how the emergent ensembles resemble those commonly reported in physiological studies. Furthermore, we compare ensembles that optimize a sustained firing code with one that optimizes a sparse code, another widely considered coding strategy, and suggest how the resulting population responses are not mutually exclusive. Finally, we demonstrate how the emergent ensembles contour the high-energy spectro-temporal modulations of natural sounds, forming a discriminative representation that captures the full range of modulation statistics that characterize natural sound ensembles. These findings have direct implications for our understanding of how sensory systems encode the informative components of natural stimuli and potentially facilitate multi-sensory integration.
BibTeX: @article{CarlinElhilali-2013, author = {Carlin, Michael A and Elhilali, Mounya}, title = {Sustained firing of model central auditory neurons yields a discriminative spectro-temporal representation for natural sounds}, journal = {PLOS Comput Biol}, publisher = {Public Library of Science}, year = {2013}, volume = {9}, number = {3}, pages = {e1002982}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1002982} }
Celikkanat, H. & Kalkan, S.	2014	Using slowness principle for feature selection: relevant feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	Signal Processing and Communications Applications Conference (SIU), 2014 22^nd , 1540-1543.	inproceedings
Abstract: We propose a novel relevant feature selection technique which makes use of the slowness principle. The slowness principle holds that physical entities in real life are subject to slow and continuous changes. Therefore, to make sense of the world, highly erratic and fast-changing signals coming to our sensors must be processed in order to extract slow and more meaningful, high-level representations of the world. This principle has been successfully utilized in previous work of Wiskott and Sejnowski, in order to implement a biologically plausible vision architecture, which allows for robust object recognition. In this work, we propose that the same principle can be extended to distinguish relevant features in the classification of a high-dimensional space. We compare our initial results with state-of-the-art ReliefF feature selection method, as well a variant of Principle Component Analysis that has been modified for feature selection. To the best of our knowledge, this is the first application of the slowness principle for the sake of relevant feature selection or classification.
BibTeX: @inproceedings{CelikkanatKalkan-2014, author = {Celikkanat, Hande and Kalkan, Sinan}, title = {Using slowness principle for feature selection: relevant feature analysis}, booktitle = {Signal Processing and Communications Applications Conference (SIU), 2014 22\textsuperscript{nd}}, year = {2014}, pages = {1540--1543}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6830535}, url2 = {http://www.kovan.ceng.metu.edu.tr/~sinan/publications/Celikkanat_SIU2014.pdf}, doi = {http://doi.org/10.1109/siu.2014.6830535} }
Celikkanat, H.; Sahin, E. & Kalkan, S.	2013	Recurrent slow feature analysis for developing object permanence in robots [Abstract] [BibTeX] [URL(2)]	IROS 2013 Workshop on Neuroscience and Robotics, Tokyo, Japan .	inproceedings
Abstract: In this work, we propose a biologically inspired framework for developing object permanence in robots. In partic- ular, we build upon a previous work on a slowness principle-based visual model (Wiskott and Sejnowski, 2002), which was shown to be adept at tracking salient changes in the environment, while seamlessly “understanding” external causes, and self-emerging structures that resemble the human visual system. We propose an extension to this architecture with a prefrontal cortex-inspired recurrent loop that enables a simple short term memory, allowing the previously reactive system to retain information through time. We argue that object permanence in humans develop in a similar manner, that is, on top a previously matured object concept. Furthermore, we show that the resulting system displays the very behaviors which are thought to be cornerstones of object permanence understanding in humans. Specifically, the system is able to retain knowledge of a hidden object’s velocity, as well as identity, through (finite) occluded periods.
BibTeX: @inproceedings{CelikkanatSahinEtAl-2013, author = {Celikkanat, Hande and Sahin, Erol and Kalkan, Sinan}, title = {Recurrent slow feature analysis for developing object permanence in robots}, booktitle = {IROS 2013 Workshop on Neuroscience and Robotics, Tokyo, Japan}, year = {2013}, url2 = {https://www.researchgate.net/profile/Hande_Celikkanat/publication/266143491_Recurrent_Slow_Feature_Analysis_for_Developing_Object_Permanence_in_Robots/links/54414fd20cf2a6a049a57142.pdf} }
Chen, Z.; Haykin, S.; Eggermont, J.J. & Becker, S.	2007	Correlation-based neural learning and machine learning [BibTeX]	Correlative Learning: A Basis for Brain and Adaptive Systems , 129-217. Publ. Wiley Online Library.	incollection
BibTeX: @incollection{ChenHaykinEtAl-2007, author = {Chen, Zhe and Haykin, Simon and Eggermont, Jos J and Becker, Suzanna}, title = {Correlation-based neural learning and machine learning}, booktitle = {Correlative Learning: A Basis for Brain and Adaptive Systems}, publisher = {Wiley Online Library}, year = {2007}, pages = {129--217} }
Cheng, C.; Liu, M.; Chen, H.; Xie, P. & Zhou, Y.	2021	Slow feature analysis-aided detection and diagnosis of incipient faults for running gear systems of high-speed trains [Abstract] [BibTeX] [URL(2)]	ISA Transactions .	article
Abstract: Incipient faults in running gear systems corrupt the overall performance of high-speed trains, increasing the necessity of fault detection and diagnosis whose purpose is to maintain the safe and stable operation of high-speed trains. For this purpose, a novel data-driven method, that utilizes Hellinger distance and slow feature analysis, is proposed in this study. By integrating Hellinger distance into slow feature analysis, a new test statistic is defined for detecting incipient faults in running gear systems. Furthermore, the hidden Markov method is developed for performing reliable fault diagnosis tasks. The salient strengths of the proposed method lie in its satisfactory fault detectability on the one hand and the considerable robustness against high-level noises on the other hand. Finally, the effectiveness of the proposed method is verified through a numerical example and a running gear system of high-speed trains under actual working conditions.
BibTeX: @article{CHENG2021, author = {Chao Cheng and Ming Liu and Hongtian Chen and Pu Xie and Yang Zhou}, title = {Slow feature analysis-aided detection and diagnosis of incipient faults for running gear systems of high-speed trains}, journal = {ISA Transactions}, year = {2021}, url2 = {https://www.sciencedirect.com/science/article/pii/S0019057821003396}, doi = {http://doi.org/10.1016/j.isatra.2021.06.023} }
Cheng, C.; Qiao, X.; Zhang, B.; Luo, H.; Zhou, Y. & Chen, H.	2021	Multiblock Dynamic Slow Feature Analysis-Based System Monitoring for Electrical Drives of High-Speed Trains [Abstract] [BibTeX] [URL]	IEEE Transactions on Instrumentation and Measurement , 70, 1-10.	article
Abstract: The electrical drive system of high-speed trains is a key subsystem to ensure the continuous supply of train power and stable operation. By the use of local information, this article presents a method called multiblock dynamic slow feature analysis (MBDSFA) with its application in the electrical drive system of high-speed trains. First, the relevance among all variables of electrical drive systems is calculated by using mutual information, based on which all variables are divided into blocks. Then, the dynamic slow feature analysis-based system monitoring scheme is employed for each subblock, and the local characteristics of electrical drive systems are analyzed via two kinds of test statistics. All subblocks are integrated based on the Bayesian inference to obtain the global monitoring results. Finally, the effectiveness and feasibility of the proposed approach are verified through the case study on the electrical drive system of high-speed trains.
BibTeX: @article{9393956, author = {Cheng, Chao and Qiao, Xinyu and Zhang, Bangcheng and Luo, Hao and Zhou, Yang and Chen, Hongtian}, title = {Multiblock Dynamic Slow Feature Analysis-Based System Monitoring for Electrical Drives of High-Speed Trains}, journal = {IEEE Transactions on Instrumentation and Measurement}, year = {2021}, volume = {70}, pages = {1-10}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9393956}, doi = {http://doi.org/10.1109/TIM.2021.3070593} }
Chong, Y.S. & Tay, Y.H.	2015	Modeling representation of videos for anomaly detection using deep learning: a review [Abstract] [BibTeX] [URL]	e-print arXiv:1505.00523 .	misc
Abstract: This review article surveys the current progresses made toward video-based anomaly detection. We address the most fundamental aspect for video anomaly detection, that is, video feature representation. Much research works have been done in finding the right representation to perform anomaly detection in video streams accurately with an acceptable false alarm rate. However, this is very challenging due to large variations in environment and human movement, and high space-time complexity due to huge dimensionality of video data. The weakly supervised nature of deep learning algorithms can help in learning representations from the video data itself instead of manually designing the right feature for specific scenes. In this paper, we would like to review the existing methods of modeling video representations using deep learning techniques for the task of anomaly detection and action recognition.
BibTeX: @misc{ChongTay-2015, author = {Chong, Yong Shean and Tay, Yong Haur}, title = {Modeling representation of videos for anomaly detection using deep learning: a review}, year = {2015}, howpublished = {e-print arXiv:1505.00523}, url = {https://arxiv.org/abs/1505.00523} }
Chu, J.; Liang, H.; Tong, Z. & Lu, W.	2017	Slow Feature Analysis for Mitotic Event Recognition. [BibTeX]	KSII Transactions on Internet & Information Systems , 11(3).	article
BibTeX: @article{ChuLiangEtAl-2017, author = {Chu, Jinghui and Liang, Hailan and Tong, Zheng and Lu, Wei}, title = {Slow Feature Analysis for Mitotic Event Recognition.}, journal = {KSII Transactions on Internet \& Information Systems}, year = {2017}, volume = {11}, number = {3}, doi = {http://doi.org/10.3837/tiis.2017.03.023} }
Corrigan, J. & Zhang, J.	2019	Nonlinear Data-driven Process Modelling using Slow Feature Analysis and Neural Networks. [Abstract] [BibTeX] [URL]	ICINCO (1) , 439-446.	inproceedings
Abstract: Slow feature analysis is a technique that extracts slowly varying latent variables from a dataset. These latent variables, known as slow features, can capture underlying dynamics when applied to process data, leading to improved generalisation when a data-driven model is built with these slow features. A method utilising slow feature analysis with neural networks is proposed in this paper for improving generalisation in nonlinear dynamic process modelling. Additionally, a method for selecting the number of dominant slow features using changes in slowness is proposed. The proposed method is applied to creating a soft sensor for estimating polymer melt index in an industrial polymerisation process to validate the method’s performance. The proposed method is compared with principal component analysis-neural network and a neural network without any latent variable method. The results from this industrial application demonstrate the effectiveness of the proposed method for improving model generalisation capability and reducing dimensionality.
BibTeX: @inproceedings{corrigan2019nonlinear, author = {Corrigan, Jeremiah and Zhang, Jie}, title = {Nonlinear Data-driven Process Modelling using Slow Feature Analysis and Neural Networks.}, booktitle = {ICINCO (1)}, year = {2019}, pages = {439--446}, url = {https://www.scitepress.org/Papers/2019/79589/79589.pdf} }
Corrigan, J. & Zhang, J.	2020	Integrating dynamic slow feature analysis with neural networks for enhancing soft sensor performance [Abstract] [BibTeX] [URL]	Computers & Chemical Engineering , 139, 106842.	article
Abstract: This paper proposes integrating slow feature analysis (SFA) with neural networks (SFA-NN) for soft sensor development. Dynamic linear SFA is applied to the easy to measure process variable data. Then the dominant slow features are selected as the inputs of a neural network to predict the difficult to measure product quality variables. SFA can capture underlying dynamics of industrial processes through the extraction of slowly varying latent variables, known as slow features. Selection of dominant slow features using scree plot is proposed. Neural networks are utilised to cope with nonlinearities present in many real industrial processes. The effectiveness of the proposed method is evaluated on two real industrial processes and is compared with slow feature regression, partial least square regression, traditional feedforward neural networks, and using principal component analysis prior to a neural network. The proposed SFA-NN gives the best generalisation performance amongst these techniques in both case studies.
BibTeX: @article{CORRIGAN2020106842, author = {Jeremiah Corrigan and Jie Zhang}, title = {Integrating dynamic slow feature analysis with neural networks for enhancing soft sensor performance}, journal = {Computers & Chemical Engineering}, year = {2020}, volume = {139}, pages = {106842}, url = {https://www.sciencedirect.com/science/article/pii/S0098135419313134}, doi = {http://doi.org/10.1016/j.compchemeng.2020.106842} }
Corrigan, J. & Zhang, J.	2021	Developing accurate data-driven soft-sensors through integrating dynamic kernel slow feature analysis with neural networks [Abstract] [BibTeX] [URL(2)]	Journal of Process Control , 106, 208-220.	article
Abstract: A data-driven soft-sensor modelling approach based on dynamic kernel slow feature analysis (KSFA) is proposed in this paper. Slow feature analysis is a feature extraction method that aims to extract slowly varying features that can capture the driving forces behind data. However, there are situations where linear SFA (LSFA) cannot capture the driving forces due to nonlinear relationships between the driving forces and input signals. KSFA is a nonlinear extension of LSFA that utilises the kernel trick to map the inputs into a higher-dimensional feature space. Extracting the nonlinear driving forces can improve soft-sensor performance by utilising the nonlinear slow features as inputs to a neural network, which provides information on the key underlying trends, with the added benefit of noise reduction. Combining KSFA with a neural network further improves soft-sensor performance for cases where nonlinear relationships between the driving forces and soft-sensor outputs are present. The effectiveness of the proposed method is first demonstrated on a numerical example, where the theoretical advantages of KSFA can be easily observed. It is then applied to a benchmark simulated industrial fed-batch penicillin process.
BibTeX: @article{CORRIGAN2021208, author = {Jeremiah Corrigan and Jie Zhang}, title = {Developing accurate data-driven soft-sensors through integrating dynamic kernel slow feature analysis with neural networks}, journal = {Journal of Process Control}, year = {2021}, volume = {106}, pages = {208-220}, url2 = {https://www.sciencedirect.com/science/article/pii/S0959152421001554}, doi = {http://doi.org/10.1016/j.jprocont.2021.09.006} }
Creutzig, F.	2008	Sufficient encoding of dynamical systems [BibTeX] [URL] [URL(2)]	Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I .	phdthesis
BibTeX: @phdthesis{Creutzig-2008, author = {Creutzig, Felix}, title = {Sufficient encoding of dynamical systems}, school = {Humboldt-Universit{\"a}t zu Berlin, Mathematisch-Naturwissenschaftliche Fakult{\"a}t I}, year = {2008}, url = {https://www.deutsche-digitale-bibliothek.de/binary/DY7X2BAULHMZZCWPBLZDZZGSKECELL2E/full/1.pdf}, url2 = {https://pdfs.semanticscholar.org/e991/09c9c6b076b9f4995cbba51165cf097f14c5.pdf} }
Creutzig, F. & Sprekeler, H.	2008	Predictive coding and the slowness principle: an information-theoretic approach. [Abstract] [BibTeX] [URL]	Neural Computation , 20(4), 1026-1041. Publ. MIT Press - Journals.	article
Abstract: Understanding the guiding principles of sensory coding strategies is a main goal in computational neuroscience. Among others, the principles of predictive coding and slowness appear to capture aspects of sensory processing. Predictive coding postulates that sensory systems are adapted to the structure of their input signals such that information about future inputs is encoded. Slow feature analysis (SFA) is a method for extracting slowly varying components from quickly varying input signals, thereby learning temporally invariant features. Here, we use the information bottleneck method to state an information-theoretic objective function for temporally local predictive coding. We then show that the linear case of SFA can be interpreted as a variant of predictive coding that maximizes the mutual information between the current output of the system and the input signal in the next time step. This demonstrates that the slowness principle and predictive coding are intimately related.
BibTeX: @article{CreutzigSprekeler-2008, author = {Creutzig, Felix and Sprekeler, Henning}, title = {Predictive coding and the slowness principle: an information-theoretic approach.}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2008}, volume = {20}, number = {4}, pages = {1026--1041}, url = {http://www.mitpressjournals.org/doi/10.1162/neco.2008.01-07-455}, doi = {http://doi.org/10.1162/neco.2008.01-07-455} }
Cunningham, J.P. & Ghahramani, Z.	2014	Linear dimensionality reduction: survey, insights, and generalizations [Abstract] [BibTeX] [URL]	https://arxiv.org/abs/1406.0873v1 .	misc
Abstract: Linear dimensionality reduction methods are a cornerstone of analyzing high dimensional data, due to their simple geometric interpretations and typically attractive computational properties. These methods capture many data features of interest, such as covariance, dynamical structure, correlation between data sets, input-output relationships, and margin between data classes. Methods have been developed with a variety of names and motivations in many fields, and perhaps as a result the deeper connections between all these methods have not been understood. Here we unify methods from this disparate literature as optimization programs over matrix manifolds. We discuss principal component analysis, factor analysis, linear multidimensional scaling, Fisher's linear discriminant analysis, canonical correlations analysis, maximum autocorrelation factors, slow feature analysis, undercomplete independent component analysis, linear regression, and more. This optimization framework helps elucidate some rarely discussed shortcomings of well-known methods, such as the suboptimality of certain eigenvector solutions. Modern techniques for optimization over matrix manifolds enable a generic linear dimensionality reduction solver, which accepts as input data and an objective to be optimized, and returns, as output, an optimal low-dimensional projection of the data. This optimization framework further allows rapid development of novel variants of classical methods, which we demonstrate here by creating an orthogonal-projection canonical correlations analysis. More broadly, we suggest that our generic linear dimensionality reduction solver can move linear dimensionality reduction toward becoming a blackbox, objective-agnostic numerical technology.
BibTeX: @misc{CunninghamGhahramani-2014, author = {Cunningham, John P and Ghahramani, Zoubin}, title = {Linear dimensionality reduction: survey, insights, and generalizations}, year = {2014}, howpublished = {https://arxiv.org/abs/1406.0873v1}, url = {https://arxiv.org/abs/1406.0873v1} }
Cunningham, J.P. & Ghahramani, Z.	2015	Linear dimensionality reduction: survey, insights, and generalizations [Abstract] [BibTeX] [URL]	Journal of Machine Learning Research , 16, 2859-2900.	article
Abstract: Linear dimensionality reduction methods are a cornerstone of analyzing high dimensional data, due to their simple geometric interpretations and typically attractive computational properties. These methods capture many data features of interest, such as covariance, dy- namical structure, correlation between data sets, input-output relationships, and margin between data classes. Methods have been developed with a variety of names and motiva- tions in many elds, and perhaps as a result the connections between all these methods have not been highlighted. Here we survey methods from this disparate literature as opti- mization programs over matrix manifolds. We discuss principal component analysis, factor analysis, linear multidimensional scaling, Fisher's linear discriminant analysis, canonical correlations analysis, maximum autocorrelation factors, slow feature analysis, sucient di- mensionality reduction, undercomplete independent component analysis, linear regression, distance metric learning, and more. This optimization framework gives insight to some rarely discussed shortcomings of well-known methods, such as the suboptimality of certain eigenvector solutions. Modern techniques for optimization over matrix manifolds enable a generic linear dimensionality reduction solver, which accepts as input data and an ob- jective to be optimized, and returns, as output, an optimal low-dimensional projection of the data. This simple optimization framework further allows straightforward general- izations and novel variants of classical methods, which we demonstrate here by creating an orthogonal-projection canonical correlations analysis. More broadly, this survey and generic solver suggest that linear dimensionality reduction can move toward becoming a blackbox, objective-agnostic numerical technology.
BibTeX: @article{CunninghamGhahramani-2015, author = {Cunningham, John P and Ghahramani, Zoubin}, title = {Linear dimensionality reduction: survey, insights, and generalizations}, journal = {Journal of Machine Learning Research}, year = {2015}, volume = {16}, pages = {2859--2900}, url = {http://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf} }
Dähne, S.	2010	Self-organization of V1 complex-cells based on slow feature analysis and retinal waves. [Abstract] [BibTeX] [URL(2)]	Bernstein Center for Computational Neuroscience, Berlin Institute of Technology, Bernstein Center for Computational Neuroscience, Berlin Institute of Technology .	mastersthesis
Abstract: The developing visual system of many mammalian species is partially structured and organized even before the onset of vision. Spontaneous neural activity, which spreads in waves across the retina, has been suggested to play a major role in these prenatal struc- turing processes. Recently, it has been shown that when employing an efficient coding strategy, such as sparse coding, these retinal activity patterns lead to basis functions that resemble optimal stimuli of simple cells in primary visual cortex (V1). Here I present the results of applying a coding strategy that optimizes for temporal slowness, namely Slow Feature Analysis (SFA), to a biologically plausible model of retinal waves. Previously, SFA has been successfully applied in modeling parts of the visual system, most notably in reproducing a rich set of complex-cell features by training SFA with natural image sequences. In this work, I was able to obtain units that share a number of properties with cortical complex-cells by training with simulated retinal waves. The results support the idea that retinal waves share relevant temporal and spatial properties with natural visual input. Hence, retinal waves seem suitable training stimuli to learn invariances and thereby shape the developing early visual system so that it is best prepared for coding input from the natural world.
BibTeX: @mastersthesis{Daehne-2010, author = {D\"ahne, Sven}, title = {Self-organization of {V1} complex-cells based on slow feature analysis and retinal waves.}, school = {Bernstein Center for Computational Neuroscience, Berlin Institute of Technology}, year = {2010}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Dahne-2010-MasterThesis-SFARetinalWaves.pdf} }
Dähne, S.; Höhne, J.; Schreuder, M. & Tangermann, M.	2011	Slow feature analysis - a tool for extraction of discriminating event-related potentials in brain-computer interfaces [Abstract] [BibTeX] [URL]	Artificial Neural Networks and Machine Learning - ICANN 2011 , Lecture Notes in Computer Science , 6791, 36-43. Eds. Honkela, T.; Duch, W.; odzisł aw; Girolami, M. & Kaski, S. Publ. Springer Berlin Heidelberg.	inproceedings
Abstract: The unsupervised signal decomposition method Slow Feature Analysis (SFA) is applied as a preprocessing tool in the context of EEG based Brain-Computer Interfaces (BCI). Classification results based on a SFA decomposition are compared to classification results obtained on Principal Component Analysis (PCA) decomposition and to those obtained on raw EEG channels. Both PCA and SFA improve classification to a large extend compared to using no signal decomposition and require between one third and half of the maximal number of components to do so. The two methods extract different information from the raw data and therefore lead to different classification results. Choosing between PCA and SFA based on classification of calibration data leads to a larger improvement in classification performance compared to using one of the two methods alone. Results are based on a large data set (n=31 subjects) of two studies using auditory Event Related Potentials for spelling applications.
BibTeX: @inproceedings{DaehneHoehneEtAl-2011, author = {D{\"a}hne, Sven and H{\"o}hne, Johannes and Schreuder, Martijn and Tangermann, Michael}, title = {Slow feature analysis - a tool for extraction of discriminating event-related potentials in brain-computer interfaces}, booktitle = {Artificial Neural Networks and Machine Learning -- ICANN 2011}, publisher = {Springer Berlin Heidelberg}, year = {2011}, volume = {6791}, pages = {36--43}, url = {http://link.springer.com/chapter/10.1007/978-3-642-21735-7_5}, doi = {http://doi.org/10.1007/978-3-642-21735-7_5} }
Dähne, S.; Müller, K.-R. & Tangermann, M.	2011	Slow feature analysis as a potential preprocessing tool in BCI [Abstract] [BibTeX] [URL] [URL(2)]	International Journal of Bioelectromagnetism , Vol. 13(2), 100-101.	article
Abstract: Here we present initial results of the unsupervised preprocessing method Slow Feature Analysis (SFA) for a BCI data set. It is the first time SFA is applied to EEG. SFA optimizes the signal representation with respect to temporal slowness. Its objective as well as its computational properties render it a possibly useful candidate for the preprocessing of BCI EEG data in order to detect task relevant components as well as components that represent artifacts or non-stationarities of the background brain activity or external sources.
BibTeX: @article{DaehneMuellerEtAl-2011, author = {D{\"a}hne, S. and M{\"u}ller, K.-R. and Tangermann, M.}, title = {Slow feature analysis as a potential preprocessing tool in {BCI}}, journal = {International Journal of Bioelectromagnetism}, year = {2011}, volume = {Vol. 13}, number = {2}, pages = {100--101}, url = {http://www.ijbem.org/volume13/number2/2011_v13_no2_100-101.pdf}, url2 = {http://www.tobi-project.org/sites/default/files/public/Publications/TOBI-122.pdf} }
Dähne, S.; Wilbert, N. & Wiskott, L.	2010	Learning complex cell units from simulated prenatal retinal waves using slow feature analysis. [BibTeX]	Interdisciplinary College 2010 . Eds. Porzel, R.; Sebanz, N. & Spitzer, M.	inproceedings
BibTeX: @inproceedings{DaehneWilbertEtAl-2010b, author = {D{\"a}hne, Sven and Wilbert, Niko and Wiskott, Laurenz}, title = {Learning complex cell units from simulated prenatal retinal waves using slow feature analysis.}, booktitle = {Interdisciplinary College 2010}, year = {2010} }
Dähne, S.; Wilbert, N. & Wiskott, L.	2009	Learning complex cell units from simulated prenatal retinal waves with slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)] [URL(3)]	Proc. 18^th Annual Computational Neuroscience Meeting (CNS'09), July 18-23, Berlin, Germany .	inproceedings
Abstract: Many properties of the developing visual system are structured and organized before the onset of vision. Spontaneous neural activity, which spreads in waves across the retina, has been suggested to play a major role in these prenatal structuring processes [1]. Recently, it has been shown that when employing an efficient coding strategy, such as sparse coding, these retinal activity patterns lead to basis functions that resemble optimal stimuli of simple cells in V1 [2]. Here we present the results of applying a coding strategy that optimizes for temporal slowness, namely Slow Feature Analysis (SFA) [3], to a biologically plausible model of retinal waves [4] (see figure 1). We also tested other wave-like inputs (sinusoidal waves, moving Gauss blobs) that allow for an analytical understanding of the results. Previously, SFA has been successfully applied in modeling parts of the visual system, most notably in reproducing a rich set of complex cell features by training SFA with natural image sequences [5]. In this work, we were able to obtain complex-cell like receptive fields in all input conditions, as displayed in figure 2. [Figure] Figure 1. Retinal wave training sequence. Snapshots of an image sequence that was generated by the retinal wave model described in [1] and used as input to SFA. A white square in the top left corner of the first image indicates the receptive field size. [Figure] Figure 2. A sample of optimal stimuli of quadratic functions found by SFA, after training with different inputs. Training sequences derived from natural images and pink noise images result in optimal stimuli (A and B, respectively) that exhibit complex cell properties as expected (compare [2]). Training with discretized moving Gaussian blobs and the retinal wave model results in optimal stimuli (C and D, respectively) that are similar to those in (A) and (B). All units show phase invariance similar to complex cells. Our results support the idea that retinal waves share relevant temporal and spatial properties with natural images. Hence, retinal waves seem suitable training stimuli to learn invariances and thereby shape the developing early visual system so that it is best prepared for coding input from the natural world. References 1. Wong ROL: Retinal waves and visual system development. Annu. Rev. Neurosci 1999, 22:28-47. 2. Albert MV, Schnabel A, Field DJ: Innate visual learning through spontaneous activity patterns. PLoS Comput Biol 2008., 4. 3. Wiskott L, Sejnowski TJ: Slow feature analysis: unsupervised learning of invariances. Neural Computation 2002, 14:715-770. 4. Godfrey KB, Swindale NV: Retinal wave behavior through activity-dependent refractory periods. PLoS Comput Biol 2007, 3:2408-2420. 5. Berkes P, Wiskott L: Slow feature analysis yields a rich repertoire of complex cell properties. J. Vision 2005, 5:579-602.
BibTeX: @inproceedings{DaehneWilbertEtAl-2009a, author = {Sven D{\"a}hne and Niko Wilbert and Laurenz Wiskott}, title = {Learning complex cell units from simulated prenatal retinal waves with slow feature analysis.}, booktitle = {Proc.\ 18\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'09), July 18--23, Berlin, Germany}, year = {2009}, url = {http://www.biomedcentral.com/1471-2202/10/S1/P129}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/DahneWilbertEtAl-2009a-ProcCNSBerlin-Abstract-SFARetinalWaves.pdf}, url3 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/DahneWilbertEtAl-2009a-ProcCNSBerlin-Poster-SFARetinalWaves.pdf}, doi = {http://doi.org/10.1186/1471-2202-10-S1-P129} }
Dähne, S.; Wilbert, N. & Wiskott, L.	2009	Learning complex cell units from simulated prenatal retinal waves with slow feature analysis. [BibTeX]	Proc. 6'th International PhD Symposium Berlin Brain Days, Dec 9-11, Berlin, Germany .	inproceedings
BibTeX: @inproceedings{DaehneWilbertEtAl-2009b, author = {Sven D{\"a}hne and Niko Wilbert and Laurenz Wiskott}, title = {Learning complex cell units from simulated prenatal retinal waves with slow feature analysis.}, booktitle = {Proc.\ 6'th International PhD Symposium Berlin Brain Days, Dec 9--11, Berlin, Germany}, year = {2009} }
Dähne, S.; Wilbert, N. & Wiskott, L.	2010	Self-organization of V1 complex cells based on slow feature analysis and retinal waves. [Abstract] [BibTeX] [URL]	Frontiers in Computational NeuroscienceProc. Bernstein Conference on Computational Neuroscience, Sep 27-Oct 1, Berlin, Germany , 4. Publ. Frontiers Media SA.	inproceedings
Abstract: The structure of the early visual system, most notably simple and complex cells in primary visual cortex(V1), is believed to be very well adapted to the statistical regularities present in its natural input (Field 1994).In fact, a number of theoretical studies have shown that some of these structural properties are optimal withrespect to certain coding objectives such as sparseness (Olshausen & Field 1996), information maximization(Bell & Sejnowski 1997), or slowness (Berkes & Wiskott 2005). These studies have also demonstrated how simple and complex cells can emerge in the process of optimizing such a coding objective by training onnatural images (or natural image sequences). However, some elements of the well-adapted structure of thevisual system are already present prior to the onset of vision and can thus not have been learned from naturalvisual input. Spontaneous neural activity, which spreads in waves across the retina, has been suggested toplay a major role in these prenatal structuring processes (Wong 1999).Here we present the results of applying a coding objective that optimizes for temporal slowness, namelySlow Feature Analysis (SFA) (Wiskott & Sejnowski 2002), to a biologically plausible model of retinal waves(Godfrey & Swindale 2007). After training with retinal wave image sequences, the resulting SFA units are subjected to sinusoidal test stimuli in order to characterize their response properties in a similar fashion as itis common practice in physiological experiments. We find that the SFA units reproduce a number of featuresreminiscent of cortical complex cells, including receptive fields with elongated and spatially segregated ONand OFF regions, several types of orientation tuning, frequency tuning, and very low F0/F1 values, which is indicative of a largely invariant response with respect to the phase (or position) of an input grating (figure 1).Further analysis of the SFA units reveals that the algorithm achieves the phase invariance by construction ofquadrature filter pairs, which is in line with classical models of complex cells.Our results support the idea that retinal waves share relevant spatial and temporal properties with naturalimages. Hence, retinal waves seem suitable training stimuli to learn invariances and thereby shape thedeveloping early visual system so that it is best prepared for coding input from the natural world.
BibTeX: @inproceedings{DaehneWilbertEtAl-2010a, author = {S. D{\"a}hne and N. Wilbert and L. Wiskott}, title = {Self-organization of {V1} complex cells based on slow feature analysis and retinal waves.}, booktitle = {Proc.\ Bernstein Conference on Computational Neuroscience, Sep 27--Oct 1, Berlin, Germany}, journal = {Frontiers in Computational Neuroscience}, publisher = {Frontiers Media {SA}}, year = {2010}, volume = {4}, url = {http://www.frontiersin.org/10.3389/conf.fncom.2010.51.00090/event_abstract}, doi = {http://doi.org/10.3389/conf.fncom.2010.51.00090} }
Dähne, S.; Wilbert, N. & Wiskott, L.	2014	Slow feature analysis on retinal waves leads to V1 complex cells. [Abstract] [BibTeX] [URL] [URL(2)]	PLoS Comput Biol , 10(5), e1003564. Publ. Public Library of Science.	article
Abstract: The developing visual system of many mammalian species is partially structured and organized even before the onset of vision. Spontaneous neural activity, which spreads in waves across the retina, has been suggested to play a major role in these prenatal structuring processes. Recently, it has been shown that when employing an efficient coding strategy, such as sparse coding, these retinal activity patterns lead to basis functions that resemble optimal stimuli of simple cells in primary visual cortex (V1). Here we present the results of applying a coding strategy that optimizes for temporal slowness, namely Slow Feature Analysis (SFA), to a biologically plausible model of retinal waves. Previously, SFA has been successfully applied to model parts of the visual system, most notably in reproducing a rich set of complex-cell features by training SFA with quasi-natural image sequences. In the present work, we obtain SFA units that share a number of properties with cortical complex-cells by training on simulated retinal waves. The emergence of two distinct properties of the SFA units (phase invariance and orientation tuning) is thoroughly investigated via control experiments and mathematical analysis of the input-output functions found by SFA. The results support the idea that retinal waves share relevant temporal and spatial properties with natural visual input. Hence, retinal waves seem suitable training stimuli to learn invariances and thereby shape the developing early visual system such that it is best prepared for coding input from the natural world.
BibTeX: @article{DaehneWilbertEtAl-2014, author = {Sven D{\"{a}}hne and Niko Wilbert and Laurenz Wiskott}, title = {Slow feature analysis on retinal waves leads to {V1} complex cells.}, journal = {PLoS Comput Biol}, publisher = {Public Library of Science}, year = {2014}, volume = {10}, number = {5}, pages = {e1003564}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1003564}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/DahneWilbertEtAl-2014-PLoSCompBiol-RetinalWaves.pdf}, doi = {http://doi.org/10.1371/journal.pcbi.1003564} }
Dawood, F. & Loo, C.K.	2014	Autonomous motion primitive segmentation of actions for incremental imitative learning of humanoid [Abstract] [BibTeX] [URL]	Robotic Intelligence In Informationally Structured Space (RiiSS), 2014 IEEE Symposium on , 1-8.	inproceedings
Abstract: During imitation learning or learning by demon-stration/observation, a crucial element of conception involves segmenting the continuous flow of motion into simpler units ÂĂŗ- motion primitives -ÂĂŗ by identifying the boundaries of an action. Secondly, in realistic environment the robot must be able to learn the observed motion patterns incrementally in a stable adaptive manner. In this paper, we propose an on-line and unsupervised motion segmentation method rendering the robot to learn actions by observing the patterns performed by other partner through Incremental Slow Feature Analysis. The segmentation model directly operates on the images acquired from the robot's vision sensor (camera) without requiring any kinematic model of the demonstrator. After segmentation, the spatio-temporal motion sequences are learned incrementally through Topological Gaussian Adaptive Resonance Hidden Markov Model. The learning model dynamically generates the topological structure in a self-organizing and self-stabilizing manner.
BibTeX: @inproceedings{DawoodLoo-2014, author = {Dawood, Farhan and Loo, Chu Kiong}, title = {Autonomous motion primitive segmentation of actions for incremental imitative learning of humanoid}, booktitle = {Robotic Intelligence In Informationally Structured Space (RiiSS), 2014 IEEE Symposium on}, year = {2014}, pages = {1--8}, url = {http://ieeexplore.ieee.org/document/7009169/}, doi = {http://doi.org/10.1109/riiss.2014.7009169} }
Dawood, F. & Loo, C.K.	2016	Incremental episodic segmentation and imitative learning of humanoid robot through self-exploration [Abstract] [BibTeX] [URL] [URL(2)]	Neurocomputing , 173, 1471-1484. Publ. Elsevier.	article
Abstract: Imitation learning through self-exploration is an essential mechanism in developing sensorimotor skills for human infants as well for robots. We assume that a primitive sense of self is the prerequisite for successful social interaction rather than an outcome of it. During imitation learning, a crucial element of conception involves segmenting the continuous flow of motion into simpler units â motion primitives â by identifying the boundaries of an action. Secondly, in realistic environment the robot must be able to learn the observed motion patterns incrementally in a stable adaptive manner without corrupting previously learned information. In this paper, we propose an on-line and unsupervised motion segmentation method allowing the robot to imitate and perform actions by observing the motion patterns performed by other partner through Incremental Kernel Slow Feature Analysis. The segmentation model directly operates on the images acquired from the robots vision sensor (camera) without requiring any kinematic model of the demonstrator. After segmentation, the spatio-temporal motion sequences are learned incrementally through Topological Gaussian Adaptive Resonance Hidden Markov Model. The learning model dynamically generates the topological structure in a self-organizing and self-stabilizing manner. Each node represents the encoded motion element (i.e. joint angles). The complete architecture was evaluated by simulation experiments performed on DARwIn-OP humanoid robot.
BibTeX: @article{DawoodLoo-2016a, author = {Farhan Dawood and Chu Kiong Loo}, title = {Incremental episodic segmentation and imitative learning of humanoid robot through self-exploration}, journal = {Neurocomputing}, publisher = {Elsevier}, year = {2016}, volume = {173}, pages = {1471--1484}, url = {http://www.sciencedirect.com/science/article/pii/S0925231215013296}, url2 = {https://pdfs.semanticscholar.org/3d66/f7015da9a127023ca240aa51672f7d0dbbe3.pdf}, doi = {http://doi.org/10.1016/j.neucom.2015.09.021} }
Dawood, F. & Loo, C.K.	2016	View-invariant visuomotor processing in computational mirror neuron system for humanoid [Abstract] [BibTeX] [URL]	PloS one , 11(3), e0152003. Publ. Public Library of Science.	article
Abstract: Mirror neurons are visuo-motor neurons found in primates and thought to be significant for imitation learning. The proposition that mirror neurons result from associative learning while the neonate observes his own actions has received noteworthy empirical support. Self-exploration is regarded as a procedure by which infants become perceptually observant to their own body and engage in a perceptual communication with themselves. We assume that crude sense of self is the prerequisite for social interaction. However, the contribution of mirror neurons in encoding the perspective from which the motor acts of others are seen have not been addressed in relation to humanoid robots. In this paper we present a computational model for development of mirror neuron system for humanoid based on the hypothesis that infants acquire MNS by sensorimotor associative learning through self-exploration capable of sustaining early imitation skills. The purpose of our proposed model is to take into account the view-dependency of neurons as a probable outcome of the associative connectivity between motor and visual information. In our experiment, a humanoid robot stands in front of a mirror (represented through self-image using camera) in order to obtain the associative relationship between his own motor generated actions and his own visual body-image. In the learning process the network first forms mapping from each motor representation onto visual representation from the self-exploratory perspective. Afterwards, the representation of the motor commands is learned to be associated with all possible visual perspectives. The complete architecture was evaluated by simulation experiments performed on DARwIn-OP humanoid robot.
BibTeX: @article{DawoodLoo-2016b, author = {Dawood, Farhan and Loo, Chu Kiong}, title = {View-invariant visuomotor processing in computational mirror neuron system for humanoid}, journal = {PloS one}, publisher = {Public Library of Science}, year = {2016}, volume = {11}, number = {3}, pages = {e0152003}, url = {http://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0152003&type=printable}, doi = {http://doi.org/10.1371/journal.pone.0152003} }
De Luca, V.; Grabner, H.; Petrusca, L.; Salomir, R.; Székely, G. & Tanner, C.	2011	Keep breathing! common motion helps multi-modal mapping [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Medical Image Computing and Computer-Assisted Intervention , 597-604. Publ. Springer Nature.	inproceedings
Abstract: We propose an unconventional approach for transferring of information between multi-modal images. It exploits the temporal commonality of multi-modal images acquired from the same organ during free-breathing. Strikingly there is no need for capturing the same region by the modalities. The method is based on extracting a low-dimensional description of the image sequences, selecting the common cause signal (breathing) for both modalities and finding the most similar sub-sequences for predicting image feature location. The approach was evaluated for 3 volunteers on sequences of 2D MRI and 2D US images of the liver acquired at different locations. Simultaneous acquisition of these images allowed for quantitative evaluation (predicted versus ground truth MRI feature locations). The best performance was achieved with signal extraction by slow feature analysis resulting in an average error of 2.6 mm (4.2 mm) for sequences acquired at the same (a different) time.
BibTeX: @inproceedings{DeLucaGrabnerEtAl-2011, author = {De Luca, Valeria and Grabner, H and Petrusca, Lorena and Salomir, Rares and Sz{\'e}kely, G{\'a}bor and Tanner, Christine}, title = {Keep breathing! common motion helps multi-modal mapping}, booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention}, publisher = {Springer Nature}, year = {2011}, pages = {597--604}, url = {http://link.springer.com/chapter/10.1007/978-3-642-23623-5_75}, url2 = {https://pdfs.semanticscholar.org/2bd3/b2e9269f9930a662710fe077f0e44e853f73.pdf}, doi = {http://doi.org/10.1007/978-3-642-23623-5_75} }
Dean, T.	2006	Learning invariant features using inertial priors [Abstract] [BibTeX] [URL] [URL(2)]	Annals of Mathematics and Artificial Intelligence , 47(3), 223-250. Publ. Springer.	article
Abstract: We address the technical challenges involved in combining key features from several theories of the visual cortex in a single coherent model. The resulting model is a hierarchical Bayesian network factored into modular component networks embedding variable-order Markov models. Each component network has an associated receptive field corresponding to components residing in the level directly below it in the hierarchy. The variable-order Markov models account for features that are invariant to naturally occurring transformations in their inputs. These invariant features give rise to increasingly stable, persistent representations as we ascend the hierarchy. The receptive fields of proximate components on the same level overlap to restore selectivity that might otherwise be lost to invariance.
BibTeX: @article{Dean-2006, author = {Dean, Thomas}, title = {Learning invariant features using inertial priors}, journal = {Annals of Mathematics and Artificial Intelligence}, publisher = {Springer}, year = {2006}, volume = {47}, number = {3}, pages = {223--250}, url = {http://link.springer.com/article/10.1007/s10472-006-9039-9}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.88.8672&rep=rep1&type=pdf}, doi = {http://doi.org/10.1007/s10472-006-9039-9} }
Deimel, R.	2009	Contextual slow feature extraction framework [Abstract] [BibTeX] [URL(2)]	University of Vienna, Austrian Research Institute for Artificial Intelligence, University of Vienna, Austrian Research Institute for Artificial Intelligence (TR-2009-06).	techreport
Abstract: The paper presents an agent-based framework for in- vestigating a class of learning algorithms that exploit temporal correlation in sensor signals. They are re- ferred to as Slow Feature Extraction (SFE) methods, such as Slow Feature Analysis (SFA) (Wiskott and Se- jnowski 2002) or spike-timing dependent neural plas- ticity (Körding and König 2001). The framework pro- vides the notion of a Context within the agent, that can be utilized to suppress or affirm certain Slow Features when analysing sensor data with SFE methods. The paper presents several possible modifications to a basic slowness criterion as used by the Slow Feature Analy- sis algorithm. Simulations with a contextualized ver- sion of SFA (cSFA) shows increased robustness of fea- ture extraction in the face of different action patterns. The framework is further shown to naturally provide a hierarchical organisation of SFE methods and for the formal description of multisensory settings, useful for investigating Correlative Learning
BibTeX: @techreport{Deimel-2009, author = {Deimel, Raphael}, title = {Contextual slow feature extraction framework}, school = {University of Vienna, Austrian Research Institute for Artificial Intelligence}, year = {2009}, number = {TR-2009-06}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.727.6036&rep=rep1&type=pdf} }
Deng, X.; Tian, X. & Hu, X.	2012	Nonlinear process fault diagnosis based on slow feature analysis [Abstract] [BibTeX] [URL]	Proceedings of the 10^th World Congress on Intelligent Control and Automation , 3152-3156. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Invariant features of temporally varying signals are very useful for process monitoring. A novel nonlinear process fault diagnosis method is proposed in this paper based on slow feature analysis (SFA) which is a new invariant learning method. In the proposed method, input-output transformation functions are optimized to extract the nonlinear slowly varying components as invariant features. Based on feature variables, two monitoring statistics are constructed for fault detection and their confidence limits are computed by kernel density estimation. Simulation using a continuous stirred tank reactor (CSTR) system shows that the proposed method outperforms the traditional PCA and KPCA method.
BibTeX: @inproceedings{DengTianEtAl-2012, author = {Xiaogang Deng and Xuemin Tian and Xiangyang Hu}, title = {Nonlinear process fault diagnosis based on slow feature analysis}, booktitle = {Proceedings of the 10\textsuperscript{th} World Congress on Intelligent Control and Automation}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2012}, pages = {3152--3156}, url = {http://ieeexplore.ieee.org/document/6358414/}, doi = {http://doi.org/10.1109/wcica.2012.6358414} }
Dong, F.; Li, L. & Zhang, S.	2021	Flow status identification based on multiple slow feature analysis of gastextendashliquid two-phase flow in horizontal pipes [Abstract] [BibTeX] [URL]	, 32(5), 055301. Publ. IOP Publishing.	article
Abstract: A gas–liquid two-phase flow is a highly complex and random process with complicated and variable flow statuses. The status identification of two-phase flows focuses on the situation of flow processes over specific time periods, as reflected by flow regimes, phase holdup, flow velocity, and other parameters. Aiming to discover how to obtain flow status information and identify the flow statuses of gas–liquid two-phase flows in horizontal pipes, a meticulous identification method based on multiple slow feature analysis combined with Bayesian inference is proposed, with concurrent monitoring of steady states and process dynamics. In this method, representational models for different typical flow regimes are established to describe both the steady states and temporal distributions. On this basis, by monitoring statistics and developing a Bayesian inference-based index, the current flow status can be identified online. Besides status identification, process dynamics are monitored to detect the dynamic characteristics of the current process with meaningful physical interpretation and deep process understanding. The application of this method to typical flow regimes and the status of transitions from bubble flow to slug flow demonstrates the feasibility and efficacy of the proposed method.
BibTeX: @article{2021, author = {Feng Dong and Linghan Li and Shumei Zhang}, title = {Flow status identification based on multiple slow feature analysis of gas{\textendash}liquid two-phase flow in horizontal pipes}, publisher = {{IOP} Publishing}, year = {2021}, volume = {32}, number = {5}, pages = {055301}, url = {https://doi.org/10.1088/1361-6501/abdae4}, doi = {http://doi.org/10.1088/1361-6501/abdae4} }
Doumanoglou, A.; Vretos, N. & Daras, P.	2019	Frequency–based slow feature analysis [Abstract] [BibTeX] [URL(2)]	Neurocomputing , 368, 34-50.	article
Abstract: Slow Feature Analysis (SFA) is an unsupervised learning algorithm which extracts slowly varying features from a temporal vectorial signal. In SFA, feature slowness is measured by the average value of its squared time-derivative. In this paper, we introduce Frequency-Based Slow Feature Analysis (FSFA) and prove that it is a generalization of SFA in the frequency domain. In FSFA, the low pass filtered versions of the extracted slow features have maximum energy, making slowness a filter dependent measurement. Experimental results show that the extracted features depend on the selected filter kernel and are different than the signals extracted using SFA. However, it is proven that there is one filter kernel that makes FSFA equivalent to SFA. Furthermore, experiments on UCF-101 video action recognition dataset, showcase that the features extracted by FSFA, with proper filter kernels, result in improved classification performance when compared to the features extracted by standard SFA. Finally, an experiment on UCF-101, with an indicative, simple and shallow neural network, being composed of FSFA and SFA nodes, demonstrates that the previously mentioned network, can transform the features extracted by a known Convolutional Neural Network to a new feature space, where classification performance through Support Vector Machine can be improved.
BibTeX: @article{DOUMANOGLOU201934, author = {Alexandros Doumanoglou and Nicholas Vretos and Petros Daras}, title = {Frequency–based slow feature analysis}, journal = {Neurocomputing}, year = {2019}, volume = {368}, pages = {34-50}, url2 = {https://www.sciencedirect.com/science/article/pii/S0925231219312056}, doi = {http://doi.org/10.1016/j.neucom.2019.08.067} }
Elkins, A.C.; Sun, Y.; Zafeiriou, S. & Pantic, M.	2013	The face of an imposter: computer vision for deception detection research in progress [Abstract] [BibTeX] [URL(2)]	. Publ. IEEE Computer Society.	misc
Abstract: Using video analyzed from a novel deception experiment, this paper introduces computer vision research in progress that addresses two critical components to computational modeling of deceptive behavior: 1) individual nonverbal behavior differences, and 2) deceptive ground truth. Video interviews analyzed for this research were participants recruited as potential hooligans (extreme sports fans) who lied about support for their rival team. From these participants, we will process and extract features representing their faces that will be submitted to slow feature analysis. From this analysis we will identify each person’s unique facial expression and behaviors, and look for systemic variation between truth and deception.
BibTeX: @misc{ElkinsSunEtAl-2013, author = {Elkins, Aaron C and Sun, Yijia and Zafeiriou, Stefanos and Pantic, Maja}, title = {The face of an imposter: computer vision for deception detection research in progress}, publisher = {IEEE Computer Society}, year = {2013}, url2 = {https://pdfs.semanticscholar.org/25f7/8f4e5c63236f7948801105352c9539e21dae.pdf} }
Escalante, A. & Wiskott, L.	2010	Gender and age estimation from synthetic face images with hierarchical slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU'10), June 28-July 2, Dortmund . Eds. Hü, E.; llermeier & Kruse, R.	inproceedings
Abstract: Our ability to recognize the gender and estimate the age of people around us is crucial for our social development and interactions. In this paper, we investigate how to use Slow Feature Analysis (SFA) to estimate gender and age from synthetic face images. SFA is a versatile unsupervised learning algorithm that extracts slowly varying features from a multidimensional signal. To process very high-dimensional data, such as images, SFA can be applied hierarchically. The key idea here is to construct the training signal such that the parameters of interest, namely gender and age, vary slowly. This makes the labelling of the data implicit in the training signal and permits the use of the unsupervised algorithm in a hierarchical fashion. A simple supervised step at the very end is then sufficient to extract gender and age with high reliability. Gender was estimated with a very high accuracy, and age had an RMSE of 3.8 years for test images.
BibTeX: @inproceedings{EscalanteWiskott-2010, author = {Alberto Escalante and Laurenz Wiskott}, title = {Gender and age estimation from synthetic face images with hierarchical slow feature analysis.}, booktitle = {International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU'10), June 28--July 2, Dortmund}, year = {2010}, url = {http://www.springerlink.com/content/r031104qv7228r35}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/EscalanteWiskott-2010-IPMU-AgeGenderEstimation-Preprint.pdf} }
Escalante, A. & Wiskott, L.	2011	Heuristic evaluation of expansions for non-linear hierarchical slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)]	Proc. The 10^th Intl. Conf. on Machine Learning and Applications (ICMLA'11), Dec. 18-21, Honolulu, Hawaii , 133-138. Publ. IEEE Computer Society, Los Alamitos, CA, USA.	inproceedings
Abstract: Slow Feature Analysis (SFA) is a feature extraction algorithm based on the slowness principle with applications to both supervised and unsupervised learning. When implemented hierarchically, it allows for efficient processing of high-dimensional data, such as images. Expansion plays a crucial role in the implementation of non-linear SFA. In this paper, a fast heuristic method for the evaluation of expansions is proposed, consisting of tests on seven problems and two metrics. Several expansions with different complexities are evaluated. It is shown that the method allows predictions of the performance of SFA on a concrete data set, and the use of normalized expansions is justified. The proposed method is useful for the design of powerful expansions that allow the extraction of complex high-level features and provide better generalization.
BibTeX: @inproceedings{EscalanteWiskott-2011, author = {Alberto Escalante and Laurenz Wiskott}, title = {Heuristic evaluation of expansions for non-linear hierarchical slow feature analysis.}, booktitle = {Proc.\ The 10\textsuperscript{th} Intl.\ Conf.\ on Machine Learning and Applications (ICMLA'11), Dec.\ 18-21, Honolulu, Hawaii}, publisher = {IEEE Computer Society}, year = {2011}, pages = {133--138}, url = {http://ieeexplore.ieee.org/document/6146957/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/EscalanteWiskott-2011-ICMLA-Expansions-Preprint.pdf}, doi = {http://doi.org/10.1109/ICMLA.2011.72} }
Escalante-B., A.N. & Wiskott, L.	2012	Slow feature analysis: perspectives for technical applications of a versatile learning algorithm [Abstract] [BibTeX] [URL] [URL(2)]	Künstliche Intelligenz [Artificial Intelligence] , 26(4), 341-348. Publ. Springer Nature.	article
Abstract: Slow Feature Analysis (SFA) is an unsupervised learning algorithm based on the slowness principle and has originally been developed to learn invariances in a model of the primate visual system. Although developed for computational neuroscience, SFA has turned out to be a versatile algorithm also for technical applications since it can be used for feature extraction, dimensionality reduction, and invariance learning. With minor adaptations SFA can also be applied to supervised learning problems such as classification and regression. In this work, we review several illustrative examples of possible applications including the estimation of driving forces, nonlinear blind source separation, traffic sign recognition, and face processing.
BibTeX: @article{Escalante-B.Wiskott-2012a, author = {Alberto N. Escalante-B. and Laurenz Wiskott}, title = {Slow feature analysis: perspectives for technical applications of a versatile learning algorithm}, journal = {K{\"u}nstliche Intelligenz [Artificial Intelligence]}, publisher = {Springer Nature}, year = {2012}, volume = {26}, number = {4}, pages = {341--348}, url = {http://www.springerlink.com/content/vk3738325250162k/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/EscalanteWiskott-2012a-KI-SFATechnicalApplications-Preprint.pdf}, doi = {http://doi.org/10.1007/s13218-012-0190-7} }
Escalante-B., A.N. & Wiskott, L.	2012	How to solve classification and regression problems on real data with slow feature analysis [BibTeX]	Poster at the 21^st Machine Learning Summer School, Aug 27 -- Sep 7, Kyoto University, Japan .	misc
BibTeX: @misc{Escalante-B.Wiskott-2012b, author = {Alberto N. Escalante-B. and Laurenz Wiskott}, title = {How to solve classification and regression problems on real data with slow feature analysis}, year = {2012}, howpublished = {Poster at the 21\textsuperscript{st} Machine Learning Summer School, Aug 27 -- Sep 7, Kyoto University, Japan} }
Escalante-B., A.N. & Wiskott, L.	2013	How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis [Abstract] [BibTeX] [URL]	Journal of Machine Learning Research , 14, 3683-3719.	article
Abstract: Supervised learning from high-dimensional data, e.g., multimedia data, is a challenging task. We propose an extension of slow feature analysis (SFA) for supervised dimensionality reduction called graph-based SFA (GSFA). The algorithm extracts a label-predictive low-dimensional set of features that can be post-processed by typical supervised algorithms to generate the final label or class estimation. GSFA is trained with a so-called training graph, in which the vertices are the samples and the edges represent similarities of the corresponding labels. A new weighted SFA optimization problem is introduced, generalizing the notion of slowness from sequences of samples to such training graphs. We show that GSFA computes an optimal solution to this problem in the considered function space, and propose several types of training graphs. For classification, the most straightforward graph yields features equivalent to those of (nonlinear) Fisher discriminant analysis. Emphasis is on regression, where four different graphs were evaluated experimentally with a subproblem of face detection on photographs. The method proposed is promising particularly when linear models are insufficient, as well as when feature selection is difficult.
BibTeX: @article{Escalante-B.Wiskott-2013b, author = {Alberto N. Escalante-B. and Laurenz Wiskott}, title = {How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis}, journal = {Journal of Machine Learning Research}, year = {2013}, volume = {14}, pages = {3683--3719}, url = {http://jmlr.org/papers/v14/escalante13a.html} }
Escalante-B., A.N. & Wiskott, L.	2015	Theoretical analysis of the optimal free responses of graph-based SFA for the design of training graphs [Abstract] [BibTeX] [URL]	e-print arXiv:1509.08329 .	misc
Abstract: Slow feature analysis (SFA) is an unsupervised learning algorithm that extracts slowly varying features from a time series. Graph-based SFA (GSFA) is a supervised extension that can solve regression problems if followed by a post-processing regression algorithm. A training graph specifies arbitrary connections between the training samples. The connections in current graphs, however, only depend on the rank of the involved labels. Exploiting the exact label values makes further improvements in estimation accuracy possible. In this article, we propose the exact label learning (ELL) method to create a graph that codes the desired label explicitly, so that GSFA is able to extract a normalized version of it directly. The ELL method is used for three tasks: (1) We estimate gender from artificial images of human faces (regression) and show the advantage of coding additional labels, particularly skin color. (2) We analyze two existing graphs for regression. (3) We extract compact discriminative features to classify traffic sign images. When the number of output features is limited, a higher classification rate is obtained compared to a graph equivalent to nonlinear Fisher discriminant analysis. The method is versatile, directly supports multiple labels, and provides higher accuracy compared to current graphs for the problems considered.
BibTeX: @misc{Escalante-B.Wiskott-2015, author = {Alberto N. Escalante-B. and Laurenz Wiskott}, title = {Theoretical analysis of the optimal free responses of graph-based {SFA} for the design of training graphs}, year = {2015}, howpublished = {e-print arXiv:1509.08329}, url = {https://arxiv.org/abs/1509.08329} }
Escalante-B., A.N. & Wiskott, L.	2016	Theoretical analysis of the optimal free responses of graph-based SFA for the design of training graphs. [Abstract] [BibTeX] [URL]	Journal of Machine Learning Research , 17(157), 1-36.	article
Abstract: Slow feature analysis (SFA) is an unsupervised learning algorithm that extracts slowly varying features from a multi-dimensional time series. Graph-based SFA (GSFA) is an extension to SFA for supervised learning that can be used to successfully solve regression problems if combined with a simple supervised post-processing step on a small number of slow features. The objective function of GSFA minimizes the squared output dierences between pairs of samples specied by the edges of a structure called training graph. The edges of current training graphs, however, are derived only from the relative order of the labels. Exploiting the exact numerical value of the labels enables further improvements in label estimation accuracy. In this article, we propose the exact label learning (ELL) method to create a more precise training graph that encodes the desired labels explicitly and allows GSFA to extract a normalized version of them directly (i.e., without supervised post-processing). The ELL method is used for three tasks: (1)We estimate gender from articial images of human faces (regression) and show the advantage of coding additional labels, particularly skin color. (2) We analyze two existing graphs for regression. (3) We extract compact discriminative features to classify trac sign images. When the number of output features is limited, such compact features provide a higher classication rate compared to a graph that generates features equivalent to those of nonlinear Fisher discriminant analysis. The method is versatile, directly supports multiple labels, and provides higher accuracy compared to current graphs for the problems considered.
BibTeX: @article{Escalante-B.Wiskott-2016b, author = {Alberto N. Escalante-B. and Laurenz Wiskott}, title = {Theoretical analysis of the optimal free responses of graph-based {SFA} for the design of training graphs.}, journal = {Journal of Machine Learning Research}, year = {2016}, volume = {17}, number = {157}, pages = {1--36}, url = {http://jmlr.org/papers/v17/15-311.html} }
Escalante-B., A.-N. & Wiskott, L.	2013	How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 8966.	misc
BibTeX: @misc{Escalante-B.Wiskott-2013a, author = {Alberto-N. Escalante-B. and Laurenz Wiskott}, title = {How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis}, year = {2013}, volume = {8966}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/8966/} }
Fan, K.; Wang, P. & Zhuang, S.	2018	Human fall detection using slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	Multimedia Tools and Applications , 78, 9101-9128.	article
Abstract: Falls are reported to be the leading causes of accidental deaths among elderly people. Automatic detection of falls from video sequences is an assistant technology for low-cost health care systems. In this paper, we present a novel slow feature analysis based framework for fall detection in a house care environment. Firstly, a foreground human body is extracted by a background subtraction technique. After morphological operations, the human silhouette is refined and covered by a fitted ellipse. Secondly, six shape features are quantified from the covered silhouette to represent different human postures. With the help of the learned slow feature functions, the shape feature sequences are transformed into slow feature sequences with discriminative information about human actions. To represent the fall incidents, the squared first order temporal derivatives of the slow features are accumulated into a classification vector. Lastly, falls are distinguished from other daily actions, such as walking, crouching, and sitting, by the trained directed acyclic graph support vector machine. Experiments on the multiple-camera fall dataset and the SDUFall dataset demonstrate that our method is comparable to other state-of-the-art methods, achieving 94.00% recognition rate on the former dataset and 96.57% on the latter one.
BibTeX: @article{Fan2018HumanFD, author = {Kaibo Fan and Ping Wang and Shuo Zhuang}, title = {Human fall detection using slow feature analysis}, journal = {Multimedia Tools and Applications}, year = {2018}, volume = {78}, pages = {9101-9128}, url = {https://link.springer.com/article/10.1007/s11042-018-5638-9}, url2 = {https://www.researchgate.net/publication/322685565_Human_fall_detection_using_slow_feature_analysis} }
Fan, K.; Wang, P.C. & Zhuang, S.	2018	Human fall detection using slow feature analysis [BibTeX]	Multimedia Tools and Applications , 1-28.	article
BibTeX: @article{FanWangEtAl-2018, author = {Kaibo Fan and Ping Chuan Wang and Shuo Zhuang}, title = {Human fall detection using slow feature analysis}, journal = {Multimedia Tools and Applications}, year = {2018}, pages = {1-28}, doi = {http://doi.org/10.1007/s11042-018-5638-9} }
Fan, L.	2020	Robust Latent Variable Modeling Using Probabilistic Slow Feature Analysis [Abstract] [BibTeX] [URL(2)]	. Publ. University of Alberta Libraries.	article
Abstract: Data-driven modeling approaches have been widely studied and applied to the process industries for inferential sensor development, process monitoring and fault detection and early warnings, etc. Essential information of process, like dynamic and relationships between process variables are buried in the massive archived historical data. They are often with high dimensionality and corrupted by diffident kinds of data irregularities, e.g. outliers, missing and multi-rate samples, uncertain time delays, etc. To address all these data irregularities and build a computational efficient modeling approach, the latent variable modeling has become a preferred and successful method. In most chemical processes, the process condition does not vary too fast and often contains large inertia. It is naturally considered that the features with small varying velocity are informative and carry most of the information of the process. With a probabilistic formulation, dynamic latent variable models, based on extracting slowly varying features, are developed in this thesis to address the aforementioned data irregularities, thus give reliable prediction results of quality variables that are otherwise difficult to measure. Outliers are observations that are distant from other observations and they are common in process variable measurements. A robust dynamic latent feature extraction model is first proposed in this thesis to handle the outlier issue. By assuming the observations following the Student’s t-distribution that has heavier tails, more weights can be assigned to the outliers thus they can be properly accounted for during modeling process. In feature extraction phase, a weighted Kalman gain is proposed since it violates the Gaussian assumption of the traditional Kalman filter. Smoother and slower features can be extracted and the impact of outliers is alleviated by the latent variance scale. The next contribution of this thesis is to develop a semi-supervised model based on probability slow feature analysis to include the information from quality variables in the extracted latent features while accounting for the missing data issues in quality variables. An approach by augmenting both input and output variables is proposed. It can deal with the different missing data issues, i.e. either missing at random or multi-rate sampling. In latent feature extracting process, the quality variable samples can be utilized whenever they are available. The compensation by the past quality variable samples leads to better predictability of its future samples. Another irregular property of the lab samples of quality variable is its uncertain time delays. In many cases, the quality variables are sampled and analyzed manually by operators if the real-time on-line analysis is not possible. Various factors during manual sampling, i.e. human errors, manual sample, lab analysis and data recording procedures, etc can result in time-varying time delays on the quality variable samples. Another latent variable, delay indicator which evolves following a hidden Markov model, is introduced in the variational Bayesian framework to address this issue. The preference of model parameters is given as their prior distributions. More accurate and meaningful dynamic latent features can be extracted using the shifted samples of quality variables. Time-varying time delays not only exist in the quality variables, but also in the fast-sampled process variables since their distributed locations in the plant. The changes of process conditions, varying velocity of flows, changing viscosity of transmission materials, etc., will cause the changes of delay to the target quality variable. The generalization formulation of the earlier work is proposed to address this issue. Multiple Markov chains are introduced to represent the different time-varying time delay sequences for different process variables. Dynamic latent features are extracted using both the shift process variables and scattered quality variable samples. With the consideration of the shifted observations, better prediction results of quality variable are provided. The validity and practicality of these proposed probabilistic latent variable modeling approaches are verified through numerical examples, benchmark simulations, experimental studies and industrial applications. Specifically, the application to the SAGD well pair water content prediction performance is improved by applying proposed methods when data irregularities are considered.
BibTeX: @article{https://doi.org/10.7939/r3-h7a2-z709, author = {Fan, Lei}, title = {Robust Latent Variable Modeling Using Probabilistic Slow Feature Analysis}, publisher = {University of Alberta Libraries}, year = {2020}, url2 = {https://era.library.ualberta.ca/items/c4861e8a-f7ef-4df2-a7d6-6184ee0c25ce}, doi = {http://doi.org/10.7939/R3-H7A2-Z709} }
Fan, L.; Kodamana, H. & Huang, B.	2019	Semi-supervised dynamic latent variable modeling: I/O probabilistic slow feature analysis approach [Abstract] [BibTeX] [URL]	AIChE Journal , 65(3), 964-979.	article
Abstract: Modeling of high dimensional dynamic data is a challenging task. The high dimensionality problem in process data is usually accounted for using latent variable models. Probabilistic slow feature analysis (PSFA) is an example of such an approach that accounts for high dimensionality while simultaneously capturing the process dynamics. However, PSFA also suffers from a drawback that it cannot use output information when determining the latent slow features. To address this lacunae, extension of the PSFA by incorporating outputs, resulting in Input-Output PSFA (IOPSFA) is proposed. IOPSFA can use both input and output information for extracting latent variables. Hence, inferential models based on IOPSFA are expected to have better predictive ability. The efficacy of the proposed approach with an industrial and a laboratory scale soft sensing case studies that have both complete and incomplete output measurements is evaluated, respectively. © 2018 American Institute of Chemical Engineers AIChE J, 65: 964–979, 2019
BibTeX: @article{https://doi.org/10.1002/aic.16481, author = {Fan, Lei and Kodamana, Hariprasad and Huang, Biao}, title = {Semi-supervised dynamic latent variable modeling: I/O probabilistic slow feature analysis approach}, journal = {AIChE Journal}, year = {2019}, volume = {65}, number = {3}, pages = {964-979}, url = {https://aiche.onlinelibrary.wiley.com/doi/abs/10.1002/aic.16481}, doi = {http://doi.org/10.1002/aic.16481} }
Fang, J.; Rüther, N.; Bellebaum, C.; Wiskott, L. & Cheng, S.	2018	The Interaction between Semantic Representation and Episodic Memory [BibTeX]	Neural Computation , 30, 293-332.	article
BibTeX: @article{FangRuetherEtAl-2018, author = {Jing Fang and Naima R{\"u}ther and Christian Bellebaum and Laurenz Wiskott and Sen Cheng}, title = {The Interaction between Semantic Representation and Episodic Memory}, journal = {Neural Computation}, year = {2018}, volume = {30}, pages = {293-332}, doi = {http://doi.org/10.1162/neco_a_01044} }
Feichtenhofer, C.; Pinz, A. & Wildes, R.P.	2014	Bags of spacetime energies for dynamic scene recognition [Abstract] [BibTeX] [URL] [URL(2)]	Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2681-2688.	inproceedings
Abstract: This paper presents a unified bag of visual word (BoW) framework for dynamic scene recognition. The approach builds on primitive features that uniformly capture spatial and temporal orientation structure of the imagery (e.g., video), as extracted via application of a bank of spatiotemporally oriented filters. Various feature encoding techniques are investigated to abstract the primitives to an intermediate representation that is best suited to dynamic scene representation. Further, a novel approach to adaptive pooling of the encoded features is presented that captures spatial layout of the scene even while being robust to situations where camera motion and scene dynamics are confounded. The resulting overall approach has been evaluated on two standard, publically available dynamic scene datasets. The results show that in comparison to a representative set of alternatives, the proposed approach outperforms the previous state-of-the-art in classification accuracy by 10%.
BibTeX: @inproceedings{FeichtenhoferPinzEtAl-2014, author = {Feichtenhofer, Christoph and Pinz, Axel and Wildes, Richard P}, title = {Bags of spacetime energies for dynamic scene recognition}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year = {2014}, pages = {2681--2688}, url = {http://ieeexplore.ieee.org/document/6909739/?arnumber=6909739}, url2 = {https://pdfs.semanticscholar.org/ea4e/3d9a4bfe3c57a3cf9ebca7313e91a8b2bd5c.pdf}, doi = {http://doi.org/10.1109/cvpr.2014.343} }
Fischer, M.J.	2016	Predictable components in global speleothem 8O [Abstract] [BibTeX] [URL]	Quaternary Science Reviews , 131, 380-392. Publ. Elsevier.	article
Abstract: The earth's iceâoceanâatmosphere system is made up of subsystems which have different dynamics and which evolve at different timescales. Examples include the slow dynamics of ice sheet growth and melting, the tropical response to precessional cycles (â¼21,000 years), and the fast dynamics of DansgaardâOeschger cycles (â¼1500 years). Since dynamical systems evolve along characteristic trajectories, they are, to some extent, predictable. Further, it should be possible to decompose any dynamical system that is made up of subsystems with discrete dynamics and characteristic timescales, into time series which capture those discrete components. This study reviews five methods which can potentially achieve this, including: Optimal Persistence Analysis (OPA), Slow Feature Analysis (SFA), Principal Trend Analysis (PTA), Average Predictability Time Decomposition (APTD) and Forecastable Components Analysis (ForeCA). These methods produce sets of components that are in some way predictable, such that each component is more predictable than the next component, but each method uses a different measure of predictability. The five methods are applied to a global dataset of speleothem Î´18O spanning the period 22â0Â kaÂ BP. The two leading predictable components are a monotonic trend, and a low-frequency oscillation with a periodicity of â¼21,000 years. The methods ForeCA and PTA\ cleanly separate these two components from higher-frequency signals. The third predictable component consists predominantly of a peak which ramps up during Heinrich Stadial 1, and falls thereafter. Furthermore, predictable components analysis can be used not only to investigate the predictability within a field, but can be extended to exploring the predictability between fields, such as between the northern hemisphere field and the southern hemisphere field. Predictable components analysis allows a better insight into the dynamical components of climate fields, and hence should be a useful tool for improving the interpretation of paleo-isotope records and other climate proxies.
BibTeX: @article{Fischer-2016, author = {Matt J. Fischer}, title = {Predictable components in global speleothem $\delta^18${O}}, journal = {Quaternary Science Reviews}, publisher = {Elsevier}, year = {2016}, volume = {131}, pages = {380--392}, url = {http://www.sciencedirect.com/science/article/pii/S0277379115001316}, doi = {http://doi.org/10.1016/j.quascirev.2015.03.024} }
Franzius, M.	2008	Slowness and sparseness for unsupervised learning of spatial and object codes from naturalistic data. [Abstract] [BibTeX] [URL]	Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I .	phdthesis
Abstract: This thesis introduces a hierarchical model for unsupervised learning from naturalistic video sequences. The model is based on the principles of slowness and sparseness. Different approaches and implementations for these principles are discussed. A variety of neuron classes in the hippocampal formation of rodents and primates codes for different aspects of space surrounding the animal, including place cells, head direction cells, spatial view cells and grid cells. In the main part of this thesis, video sequences from a virtual reality environment are used for training the hierarchical model. The behavior of most known hippocampal neuron types coding for space are reproduced by this model. The type of representations generated by the model is mostly determined by the movement statistics of the simulated animal. The model approach is not limited to spatial coding. An application of the model to invariant object recognition is described, where artificial clusters of spheres or rendered fish are presented to the model. The resulting representations allow a simple extraction of the identity of the object presented as well as of its position and viewing angle.
BibTeX: @phdthesis{Franzius-2008, author = {Mathias Franzius}, title = {Slowness and sparseness for unsupervised learning of spatial and object codes from naturalistic data.}, school = {Humboldt-Universit{\"{a}}t zu Berlin, Mathematisch-Naturwissenschaftliche Fakult{\"{a}}t I}, year = {2008}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?id=29124} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2007	Slowness and sparseness lead to place-, head direction-, and spatial-view cells. [Abstract] [BibTeX] [URL]	Proc. 3^rd Annual Computational Cognitive Neuroscience Conference, Nov 1-2, San Diego, USA , III-8. Eds. Becker, S. & others	inproceedings
Abstract: We present a model for the self-organized formation of place cells, head-direction cells, and spatial-view cells in the hippocampal formation based on unsupervised learning on quasi-natural visual stimuli. The model comprises a hierarchy of Slow Feature Analysis (SFA) nodes, which were recently shown to reproduce many properties of complex cells in the early visual system [1]. The system extracts a distributed grid-like representation of position and orientation, which is transcoded into a localized place-field, head-direction, or view representation, by sparse coding. The type of cells that develops depends solely on the relevant input statistics, i.e., the movement pattern of the simulated animal. The numerical simulations are complemented by a mathematical analysis that allows us to accurately predict the output of the top SFA layer.
BibTeX: @inproceedings{FranziusSprekelerEtAl-2007e, author = {Mathias Franzius and Henning Sprekeler and Laurenz Wiskott}, title = {Slowness and sparseness lead to place-, head direction-, and spatial-view cells.}, booktitle = {Proc.\ 3\textsuperscript{rd} Annual Computational Cognitive Neuroscience Conference, Nov 1--2, San Diego, USA}, year = {2007}, pages = {III-8}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.0030166}, doi = {http://doi.org/10.1371/journal.pcbi.0030166} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2007	Unsupervised learning of visually driven place cells in the hippocampus. [BibTeX]	Kognitionsforschung 2007, Beiträge zur 8. Jahrestagung der Gesellschaft für Kognitionswissenschaft (KogWis'07), Mar 19-21, Saarbrücken, Germany , 60. Eds. Frings, C.; Mecklinger, A.; Opitz, B.; Pospeschill, M.; Wentura, D. & Zimmer, H. D. Publ. Shaker Verlag, Aachen.	inproceedings
BibTeX: @inproceedings{FranziusSprekelerEtAl-2007a, author = {M. Franzius and H. Sprekeler and L. Wiskott}, title = {Unsupervised learning of visually driven place cells in the hippocampus.}, booktitle = {Kognitionsforschung 2007, Beitr{\"a}ge zur 8. Jahrestagung der Gesellschaft f\"ur Kognitionswissenschaft (KogWis'07), Mar 19-21, Saarbr\"ucken, Germany}, publisher = {Shaker Verlag}, year = {2007}, pages = {60} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2006	Slowness leads to place cells. [BibTeX]	Proc. Berlin Neuroscience Forum, Jun 8-10, Bad Liebenwalde, Germany , 42. Publ. Max-Delbrück-Centrum für Molekulare Medizin (MDC), Berlin.	inproceedings
BibTeX: @inproceedings{FranziusSprekelerEtAl-2006a, author = {M. Franzius and H. Sprekeler and L. Wiskott}, title = {Slowness leads to place cells.}, booktitle = {Proc.\ Berlin Neuroscience Forum, Jun 8--10, Bad Liebenwalde, Germany}, publisher = {Max-Delbr\"uck-Centrum f\"ur Molekulare Medizin (MDC)}, year = {2006}, pages = {42} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2006	Slowness leads to place cells. [BibTeX]	Proc. 2^nd Bernstein Symposium for Computational Neuroscience, Oct 1-3, Berlin, Germany , 45. Publ. Bernstein Center for Computational Neuroscience (BCCN) Berlin.	inproceedings
BibTeX: @inproceedings{FranziusSprekelerEtAl-2006b, author = {M. Franzius and H. Sprekeler and L. Wiskott}, title = {Slowness leads to place cells.}, booktitle = {Proc.\ 2\textsuperscript{nd} Bernstein Symposium for Computational Neuroscience, Oct 1--3, Berlin, Germany}, publisher = {Bernstein Center for Computational Neuroscience (BCCN) Berlin}, year = {2006}, pages = {45} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2006	Slowness leads to place cells. [BibTeX]	Proc. 15^th Annual Computational Neuroscience Meeting (CNS'06), Jul 16-20, Edinburgh, Scotland .	inproceedings
BibTeX: @inproceedings{FranziusSprekelerEtAl-2006c, author = {M. Franzius and H. Sprekeler and L. Wiskott}, title = {Slowness leads to place cells.}, booktitle = {Proc.\ 15\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'06), Jul 16--20, Edinburgh, Scotland}, year = {2006} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2007	Unsupervised learning of place cells and head direction cells with slow feature analysis. [BibTeX]	Proc. 7^th Göttingen Meeting of the German Neuroscience Society, Mar 29 - Apr 1, Göttingen, Germany , TS19-1C.	inproceedings
BibTeX: @inproceedings{FranziusSprekelerEtAl-2007b, author = {M. Franzius and H. Sprekeler and L. Wiskott}, title = {Unsupervised learning of place cells and head direction cells with slow feature analysis.}, booktitle = {Proc.\ 7\textsuperscript{th} G\"ottingen Meeting of the German Neuroscience Society, Mar 29 -- Apr 1, G\"ottingen, Germany}, year = {2007}, pages = {TS19--1C} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2007	Learning of place cells, head-direction cells, and spatial-view cells with slow feature analysis on quasi-natural videos. [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 5492.	misc
BibTeX: @misc{FranziusSprekelerEtAl-2007c, author = {Mathias Franzius and Henning Sprekeler and Laurenz Wiskott}, title = {Learning of place cells, head-direction cells, and spatial-view cells with slow feature analysis on quasi-natural videos.}, year = {2007}, volume = {5492}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/5492/} }
Franzius, M.; Sprekeler, H. & Wiskott, L.	2007	Slowness and sparseness lead to place, head-direction, and spatial-view cells. [Abstract] [BibTeX] [URL] [URL(2)]	PLoS Computational Biology , 3(8), e166.	article
Abstract: We present a model for the self-organized formation of place cells, head-direction cells, and spatial-view cells in the hippocampal formation based on unsupervised learning on quasi-natural visual stimuli. The model comprises a hierarchy of Slow Feature Analysis (SFA) nodes, which were recently shown to reproduce many properties of complex cells in the early visual system [1]. The system extracts a distributed grid-like representation of position and orientation, which is transcoded into a localized place-field, head-direction, or view representation, by sparse coding. The type of cells that develops depends solely on the relevant input statistics, i.e., the movement pattern of the simulated animal. The numerical simulations are complemented by a mathematical analysis that allows us to accurately predict the output of the top SFA layer.
BibTeX: @article{FranziusSprekelerEtAl-2007d, author = {Mathias Franzius and Henning Sprekeler and Laurenz Wiskott}, title = {Slowness and sparseness lead to place, head-direction, and spatial-view cells.}, journal = {PLoS Computational Biology}, year = {2007}, volume = {3}, number = {8}, pages = {e166}, url = {http://www.ploscompbiol.org/article/info%3Adoi/10.1371/journal.pcbi.0030166}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/FranziusSprekelerEtAl-2007d-PLoSCompBiol-PlaceCells.pdf}, doi = {http://doi.org/10.1371/journal.pcbi.0030166} }
Franzius, M.; Vollgraf, R. & Wiskott, L.	2006	From grids to places. [Abstract] [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 5101.	misc
Abstract: Hafting et al. (2005) described grid cells in the dorsocaudal region of the medial enthorinal cortex (dMEC). These cells show a strikingly regular grid-like firing-pattern as a function of the position of a rat in an enclosure. Since the dMEC projects to the hippocampal areas containing the well-known place cells, the question arises whether and how the localized responses of the latter can emerge based on the output of grid cells. Here, we show that, starting with simulated grid-cells, a simple linear transformation maximizing sparseness leads to a localized representation similar to place fields.
BibTeX: @misc{FranziusVollgrafEtAl-2006, author = {Mathias Franzius and Roland Vollgraf and Laurenz Wiskott}, title = {From grids to places.}, year = {2006}, volume = {5101}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/5101/} }
Franzius, M.; Vollgraf, R. & Wiskott, L.	2007	From grids to places. [Abstract] [BibTeX] [URL] [URL(2)]	Journal of Computational Neuroscience , 22(3), 297-299.	article
Abstract: Hafting et al. (2005) described grid cells in the dorsocaudal region of the medial enthorinal cortex (dMEC). These cells show a strikingly regular grid-like firing-pattern as a function of the position of a rat in an enclosure. Since the dMEC projects to the hippocampal areas containing the well-known place cells, the question arises whether and how the localized responses of the latter can emerge based on the output of grid cells. Here, we show that, starting with simulated grid-cells, a simple linear transformation maximizing sparseness leads to a localized representation similar to place fields.
BibTeX: @article{FranziusVollgrafEtAl-2007-SFA, author = {Mathias Franzius and Roland Vollgraf and Laurenz Wiskott}, title = {From grids to places.}, journal = {Journal of Computational Neuroscience}, year = {2007}, volume = {22}, number = {3}, pages = {297--299}, url = {http://www.springerlink.com/content/r6lj66670057871q/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/FranziusVollgrafEtAl-2007-JCompNeurosci-GridsToPlaces-Preprint.pdf}, doi = {http://doi.org/10.1007/s10827-006-0013-7} }
Franzius, M. & Wersing, H.	2010	Learning invariant visual shape representations from physics [Abstract] [BibTeX] [URL] [URL(2)]	Artificial Neural Networks - ICANN 2010 , Lecture Notes in Computer Science , 6354, 298-302. Eds. Diamantaras, K.; Duch, W. & Iliadis, L. Publ. Springer Berlin Heidelberg.	inproceedings
Abstract: 3D shape determines an object’s physical properties to a large degree. In this article, we introduce an autonomous learning system for categorizing 3D shape of simulated objects from single views. The system extends an unsupervised bottom-up learning architecture based on the slowness principle with top-down information derived from the physical behavior of objects. The unsupervised bottom-up learning leads to pose invariant representations. Shape specificity is then integrated as top-down information from the movement trajectories of the objects. As a result, the system can categorize 3D object shape from a single static object view without supervised postprocessing.
BibTeX: @inproceedings{FranziusWersing-2010, author = {Franzius, Mathias and Wersing, Heiko}, title = {Learning invariant visual shape representations from physics}, booktitle = {Artificial Neural Networks -- ICANN 2010}, publisher = {Springer Berlin Heidelberg}, year = {2010}, volume = {6354}, pages = {298--302}, url = {http://link.springer.com/chapter/10.1007/978-3-642-15825-4_38}, url2 = {https://pdfs.semanticscholar.org/bb8c/c7906f1d16fc8806fd21408992a68a307dbf.pdf}, doi = {http://doi.org/10.1007/978-3-642-15825-4_38} }
Franzius, M. & Wersing, H.	2014	Robot with vision-based 3D shape recognition [BibTeX]	. Publ. Google Patents.	misc
BibTeX: @misc{FranziusWersing-2014, author = {Franzius, Mathias and Wersing, Heiko}, title = {Robot with vision-based {3D} shape recognition}, publisher = {Google Patents}, year = {2014} }
Franzius, M.; Wilbert, N. & Wiskott, L.	2008	Invariant object recognition with slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)]	Proc. 18^th Intl. Conf. on Artificial Neural Networks (ICANN'08), Prague , Lecture Notes in Computer Science , 5163, 961-970. Eds. Kurková, V.; Neruda, R.; Koutní, J. & k Publ. Springer.	inproceedings
Abstract: Primates are very good at recognizing objects independently of viewing angle or retinal position and outperform existing computer vision systems by far. But invariant object recognition is only one prerequisite for successful interaction with the environment. An animal also needs to assess an object’s position and relative rotational angle. We propose here a model that is able to extract object identity, position, and rotation angles, where each code is independent of all others. We demonstrate the model behavior on complex three-dimensional objects under translation and in-depth rotation on homogeneous backgrounds. A similar model has previously been shown to extract hippocampal spatial codes from quasi-natural videos. The rigorous mathematical analysis of this earlier application carries over to the scenario of invariant object recognition.
BibTeX: @inproceedings{FranziusWilbertEtAl-2008b, author = {Mathias Franzius and Niko Wilbert and Laurenz Wiskott}, title = {Invariant object recognition with slow feature analysis.}, booktitle = {Proc.\ 18\textsuperscript{th} Intl.\ Conf.\ on Artificial Neural Networks (ICANN'08), Prague}, publisher = {Springer}, year = {2008}, volume = {5163}, pages = {961--970}, url = {http://link.springer.com/chapter/10.1007/978-3-540-87536-9_98}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/FranziusWilbertEtAl-2008b-ProcICANN-SFAInvariances2D.pdf}, doi = {http://doi.org/10.1007/978-3-540-87536-9_98} }
Franzius, M.; Wilbert, N. & Wiskott, L.	2007	Unsupervised learning of invariant 3D-object representations with slow feature analysis. [BibTeX]	Proc. 3^rd Bernstein Symposium for Computational Neuroscience, Sep 24-27, Göttingen, Germany , 105. Publ. Bernstein Center for Computational Neuroscience (BCCN) Göttingen.	inproceedings
BibTeX: @inproceedings{FranziusWilbertEtAl-2007, author = {Mathias Franzius and Niko Wilbert and Laurenz Wiskott}, title = {Unsupervised learning of invariant 3{D}-object representations with slow feature analysis.}, booktitle = {Proc.\ 3\textsuperscript{rd} Bernstein Symposium for Computational Neuroscience, Sep 24--27, G\"ottingen, Germany}, publisher = {Bernstein Center for Computational Neuroscience (BCCN) G\"ottingen}, year = {2007}, pages = {105} }
Franzius, M.; Wilbert, N. & Wiskott, L.	2008	Unsupervised learning of invariant 3D-object and pose representations with slow feature analysis. [BibTeX]	Proc. Federation of European Neuroscience Societies Forum (FENS'08), Jul 12-16, Geneva, Switzerland .	inproceedings
BibTeX: @inproceedings{FranziusWilbertEtAl-2008a, author = {Mathias Franzius and Niko Wilbert and Laurenz Wiskott}, title = {Unsupervised learning of invariant 3{D}-object and pose representations with slow feature analysis.}, booktitle = {Proc.\ Federation of European Neuroscience Societies Forum (FENS'08), Jul 12--16, Geneva, Switzerland}, year = {2008} }
Franzius, M.; Wilbert, N. & Wiskott, L.	2011	Invariant object recognition and pose estimation with slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 23(9), 2289-2323. Publ. MIT Press - Journals.	article
Abstract: Primates are very good at recognizing objects independent of viewing angle or retinal position, and they outperform existing computer vision systems by far. But invariant object recognition is only one prerequisite for successful interaction with the environment. An animal also needs to assess an object's position and relative rotational angle. We propose here a model that is able to extract object identity, position, and rotation angles. We demonstrate the model behavior on complex three-dimensional objects under translation and rotation in depth on a homogeneous background. A similar model has previously been shown to extract hippocampal spatial codes from quasi-natural videos. The framework for mathematical analysis of this earlier application carries over to the scenario of invariant object recognition. Thus, the simulation results can be explained analytically even for the complex high-dimensional data we employed.
BibTeX: @article{FranziusWilbertEtAl-2011, author = {Franzius, Mathias and Wilbert, Niko and Wiskott, Laurenz}, title = {Invariant object recognition and pose estimation with slow feature analysis.}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2011}, volume = {23}, number = {9}, pages = {2289--2323}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00171}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/FranziusWilbertEtAl-2011-NeurComp.pdf}, doi = {http://doi.org/10.1162/NECO_a_00171} }
Fritsch, J.; Kühnl, T. & Kummert, F.	2014	Monocular road terrain detection by combining visual and spatial information [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Intelligent Transportation Systems , 15(4), 1586-1596. Publ. IEEE.	article
Abstract: For future driver assistance systems and autonomous vehicles, the road course, i.e., the width and shape of the driving path, is an important source of information. In this paper, we introduce a new hierarchical two-stage approach for learning the spatial layout of road scenes. In the first stage, base classifiers analyze the local visual properties of patches extracted from monocular camera images and provide metric confidence maps. We use classifiers for road appearance, boundary appearance, and lane-marking appearance. The core of the proposed approach is the computation of SPatial RAY (SPRAY) features from each metric confidence map in the second stage. A boosting classifier selecting discriminative SPRAY features can be trained for different types of road terrain and allows capturing the local visual properties together with their spatial layout in the scene. In this paper, the extraction of road area and ego-lane on inner-city video streams is demonstrated. In particular, the detection of the ego-lane is a challenging semantic segmentation task showing the power of SPRAY features, because on a local appearance level, the ego-lane is not distinguishable from other lanes. We have evaluated our approach operating at 20 Hz on a graphics processing unit on a publicly available data set, demonstrating the performance on a variety of road types and weather conditions.
BibTeX: @article{FritschKuehnlEtAl-2014, author = {Fritsch, Jannik and K{\"{u}}hnl, Tobias and Kummert, Franz}, title = {Monocular road terrain detection by combining visual and spatial information}, journal = {IEEE Transactions on Intelligent Transportation Systems}, publisher = {IEEE}, year = {2014}, volume = {15}, number = {4}, pages = {1586--1596}, url = {http://ieeexplore.ieee.org/document/6766705/}, url2 = {https://pdfs.semanticscholar.org/73b1/10df4809d0a015f90fa6e7a7dce351bcc52e.pdf}, doi = {http://doi.org/10.1109/tits.2014.2303899} }
Gao, J. & Ye, M.	2010	Comparison of SFA and ICA [Abstract] [BibTeX] [URL]	Advanced Computational Intelligence (IWACI), 2010 Third International Workshop on , 62-65.	inproceedings
Abstract: Recently, a new method that slow feature analysis (SFA), which can extract slowly varying feature of temporally varying signals, has been explored. SFA method is an extension of independent component analysis (ICA), which has been used to separate blind source signals. In this article, we present a simple and efficient SFA based method to separate blind signals according to their different smooth degree. The performance of the proposed mathod is higher than that of the conventional method ICA. Simulation illustrates the good performance of the proposed method.
BibTeX: @inproceedings{GaoYe-2010, author = {Gao, Jianbin and Ye, Mao}, title = {Comparison of {SFA} and {ICA}}, booktitle = {Advanced Computational Intelligence (IWACI), 2010 Third International Workshop on}, year = {2010}, pages = {62--65}, url = {http://ieeexplore.ieee.org/document/5585205/}, doi = {http://doi.org/10.1109/iwaci.2010.5585205} }
Gao, J. & Zhao, C.	2018	Distributed Bayesian network with slow feature analysis for fault diagnosis [BibTeX]	2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC) , 1100-1105.	article
BibTeX: @article{GaoZhao-2018, author = {Jie Gao and Chunhui Zhao}, title = {Distributed Bayesian network with slow feature analysis for fault diagnosis}, journal = {2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)}, year = {2018}, pages = {1100-1105}, doi = {http://doi.org/10.1109/yac.2018.8406535} }
Gao, J. & Zhao, C.	2018	Distributed Bayesian network with slow feature analysis for fault diagnosis [BibTeX]	2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC) , 1100-1105.	inproceedings
BibTeX: @inproceedings{GaoZhao-2018a, author = {Gao, Jie and Zhao, Chunhui}, title = {Distributed Bayesian network with slow feature analysis for fault diagnosis}, booktitle = {2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)}, year = {2018}, pages = {1100--1105}, doi = {http://doi.org/10.1109/yac.2018.8406535} }
Gao, J.-B.; Li, J.-P. & Xia, Q.	2008	Slowly feature analysis of Gabor feature for face recognition [Abstract] [BibTeX] [URL]	2008 International Conference on Apperceiving Computing and Intelligence Analysis , 177-180. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Obtaining invariant representation of time varying signals is one of the major problems in object recognition. Recently, a new method that slowly feature analysis (SFA) which can extract invariant features of temporally varying signals is being explored, which is an extension of independent component analysis (ICA) which has been used for extracting facial feature. The technique of SFA can be extended to the field of face recognition easily. The Gabor feature face images exhibit strong characteristics of spatial locality, scale, and orientation selectivity. Theses images can produce pronounced local feature that are most suitable for face recognition. SFA would further reduce redundancy and represent slowly varying features explicitly. These slowly varying features are most useful for subsequent pattern discrimination and associative recall. Making use of the slowly feature method, in this paper, we propose a new face recognition algorithm based on Gabor face feature and slowly varying feature analysis. Results indicate that our algorithm is effective and competitive.
BibTeX: @inproceedings{GaoLiEtAl-2008, author = {Jian-Bin Gao and Jian-Ping Li and Qi Xia}, title = {Slowly feature analysis of {G}abor feature for face recognition}, booktitle = {2008 International Conference on Apperceiving Computing and Intelligence Analysis}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2008}, pages = {177--180}, url = {http://ieeexplore.ieee.org/document/4769999/}, doi = {http://doi.org/10.1109/ICACIA.2008.4769999} }
Gao, X.; Li, H.; Wang, Y.; Chen, T.; Zuo, X. & Zhong, L.	2018	Fault Detection in Managed Pressure Drilling Using Slow Feature Analysis [Abstract] [BibTeX] [URL]	IEEE Access , 6, 34262-34271.	article
Abstract: Correct detection of drilling abnormal incidents while minimizing false alarms is a crucial measure to decrease the non-productive time and, thus, decrease the total drilling cost. With the recent development of drilling technology and innovation of down-hole signal transmitting method, abundant drilling data are collected and stored in the electronic driller's database. The availability of such data provides new opportunities for rapid and accurate fault detection; however, data-driven fault detection has seen limited practical application in well drilling processes. One particular concern is how to distinguish “controllable”process changes, e.g., due to set-point changes, from truly abnormal events that should be considered as faults. This is highly relevant for the managed pressure drilling technology, where the operating pressure window is often narrow resulting in necessary set-point changes at different depths. However, the classical data-driven fault detection methods, such as principal component analysis and independent component analysis, are unable to distinguish normal set-point changes from abnormal faults. To address this challenge, a slow feature analysis (SFA)-based fault detection method is applied. The SFA-based method furnishes four monitoring charts containing more information that could be synthetically utilized to correctly differentiate set-point changes from faults. Furthermore, the evaluation about controller performance is provided for drilling operator. Simulation studies with a commercial high-fidelity simulator, Drillbench, demonstrate the effectiveness of the introduced approach.
BibTeX: @article{8383679, author = {Gao, Xiaoyong and Li, Haishou and Wang, Yuhong and Chen, Tao and Zuo, Xin and Zhong, Lei}, title = {Fault Detection in Managed Pressure Drilling Using Slow Feature Analysis}, journal = {IEEE Access}, year = {2018}, volume = {6}, pages = {34262-34271}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8383679}, doi = {http://doi.org/10.1109/ACCESS.2018.2846295} }
Gao, X.; Li, H.; Wang, Y.; Chen, T.; Zuo, X. & Zhong, L.	2018	Fault Detection in Managed Pressure Drilling Using Slow Feature Analysis [BibTeX]	IEEE Access , 6, 34262-34271. Publ. Institute of Electrical and Electronics Engineers.	article
BibTeX: @article{GaoLiEtAl-2018, author = {Xiaoyong Gao and Hao Li and Yuhong Wang and Tao Chen and Xin Zuo and Lei Zhong}, title = {Fault Detection in Managed Pressure Drilling Using Slow Feature Analysis}, journal = {IEEE Access}, publisher = {Institute of Electrical and Electronics Engineers}, year = {2018}, volume = {6}, pages = {34262-34271}, doi = {http://doi.org/10.1109/access.2018.2846295} }
Gao, X.; Shang, C.; Yang, F. & Huang, D.	2015	Detecting and isolating plant-wide oscillations via slow feature analysis [Abstract] [BibTeX] [URL]	2015 American Control Conference (ACC) , 906-911.	inproceedings
Abstract: This paper aims at detecting and isolating multiple sources of oscillations in control loops via slow feature analysis. The control loops in the process industries are usually coupled, and therefore disturbances can propagate to downstream process variables through energy or material flows and thus plant-wide disturbances arise. A significant portion of disturbances are oscillatory, and the root causes may be poor controller design or equipment faults such as valve stiction. It is important to find out locations of these oscillation sources so that further root cause diagnosis is possible. A new technique termed as slow feature analysis (SFA) is applied to detect plant-wide oscillations and isolate the sources at the loop level. SFA can recover slowly varying source signals from observed data. Since most oscillations in the process industries have low oscillatory frequencies, SFA is a very powerful tool to recover oscillation sources from observed process data. Two projection-based indices, CCI and CSI, are derived to investigate how the control loops are affected by the oscillations and isolate oscillation sources at the loop level. A simulation case study is presented to demonstrate the effectiveness of the proposed method.
BibTeX: @inproceedings{GaoShangEtAl-2015, author = {Gao, Xinqing and Shang, Chao and Yang, Fan and Huang, Dexian}, title = {Detecting and isolating plant-wide oscillations via slow feature analysis}, booktitle = {2015 American Control Conference (ACC)}, year = {2015}, pages = {906--911}, url = {http://ieeexplore.ieee.org/document/7170849/}, doi = {http://doi.org/10.1109/acc.2015.7170849} }
Gao, X. & Shardt, Y.A.W.	2021	Dynamic system modelling and process monitoring based on long-term dependency slow feature analysis [Abstract] [BibTeX] [URL(2)]	Journal of Process Control , 105, 27-47.	article
Abstract: Modern industrial processes are large-scale, highly complex systems with many units and equipment. The complex flow of mass and energy, as well as the compensation effects of closed-loop control systems, cause significant cross-correlation and autocorrelation between process variables. To operate the process systems stably and efficiently, it is crucial to uncover the inherent characteristics of both the variance structure and dynamic relationship. Compared with the original slow feature analysis (SFA) that can only model the one-step time dependence, long-term dependency slow feature analysis (LTSFA) proposed in this paper can understand the longer-term dynamics by an explicit expression of latent states of the process. An iterative algorithm is developed for the model parameter optimization and its convergency is proved. The model properties and theoretical comparison with existing dynamic models are presented. A process monitoring strategy is designed based on LTSFA. The results of two simulation case studies show that LTSFA has better system dynamics extraction capability, which reduces the violation rate of the residual for the 95% confidence interval from 40.4% to 3.2% compared to the original SFA, and can disentangle the quickly- and slowly-varying features. Several typical disturbances can be correctly identified by LTSFA. The monitoring results on the Tennessee Eastman process benchmark show the overall advantages of the proposed method both in the dynamic and nominal deviation detection and the monitoring accuracy
BibTeX: @article{GAO202127, author = {Xinrui Gao and Yuri A.W. Shardt}, title = {Dynamic system modelling and process monitoring based on long-term dependency slow feature analysis}, journal = {Journal of Process Control}, year = {2021}, volume = {105}, pages = {27-47}, url2 = {https://www.sciencedirect.com/science/article/pii/S0959152421001086}, doi = {http://doi.org/10.1016/j.jprocont.2021.07.007} }
Gao, X. & Shardt, Y.A.W.	2021	Long-term dependency slow feature analysis for dynamic process monitoring [Abstract] [BibTeX] [URL]	IFAC-PapersOnLine , 54(3), 421-426.	article
Abstract: Industrial processes are large scale, highly complex systems. The complex flow of mass and energy, as well as the compensation effects of closed-loop control systems, cause significance cross-correlation and autocorrelation between process variables. To operate the process systems stably and efficiently, it is crucial to uncover the inherent characteristics of both variance structure and dynamic relationship. Long-term dependency slow feature analysis (LTSFA) is proposed in this paper to overcome the Markov assumption of the original slow feature analysis to understand the long-term dynamics of processes, based on which a monitoring procedure is designed. A simulation example and the Tennessee Eastman process benchmark are studied to show the performance of LTSFA. The proposed method can better extract the system dynamics and monitor the process variations using fewer slow features.
BibTeX: @article{GAO2021421, author = {Xinrui Gao and Yuri A.W. Shardt}, title = {Long-term dependency slow feature analysis for dynamic process monitoring}, journal = {IFAC-PapersOnLine}, year = {2021}, volume = {54}, number = {3}, pages = {421-426}, url = {https://www.sciencedirect.com/science/article/pii/S240589632101051X}, doi = {http://doi.org/10.1016/j.ifacol.2021.08.278} }
Gao, Y.; Wang, Y. & Zhou, B.	2021	Using Slow Feature Analysis and a Cloud-Free Auxiliary Image to Remove Thin Clouds in Landsat-5 VINIR Band Data [Abstract] [BibTeX] [URL]	2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS , 7156-7159.	inproceedings
Abstract: An algorithm using slow feature analysis and a cloud-free auxiliary image was proposed to remove thin clouds within Landsat-5 visible and near-infrared (VINIR) band data. The study area was near Norwalk, CA, USA. Five 800 (rows)× 800 (columns) Landsat-5 images acquired on different dates were studied. Image one was cloud-covered. Image two, a cloud-free one acquired 16 days after image one, was used as the reference image. Images 3–5 were three cloud-free auxiliary images. The algorithm without using an auxiliary image was applied to removing thin clouds in image one. Some clouds were removed, but cloud residuals remained. With the reference image, R^2 values were computed, ranging from 0.6039 to 0.8750 for four bands. Then, the algorithm using auxiliary image one was employed to remove the clouds in image one. The removal was improved as the residuals decreased and R^2 values increased. The algorithm's performance might not be so sensitive to auxiliary images' acquisition dates as the cloud-removal results using images 3–5 were similar.
BibTeX: @inproceedings{9553259, author = {Gao, Yue and Wang, Yong and Zhou, Binxing}, title = {Using Slow Feature Analysis and a Cloud-Free Auxiliary Image to Remove Thin Clouds in Landsat-5 VINIR Band Data}, booktitle = {2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS}, year = {2021}, pages = {7156-7159}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9553259}, doi = {http://doi.org/10.1109/IGARSS47720.2021.9553259} }
Ghosh, R.; Siyi, T.; Rasouli, M.; Thakor, N.V. & Kukreja, S.L.	2016	Pose-invariant object recognition for event-based vision with slow-ELM [Abstract] [BibTeX] [URL]	International Conference on Artificial Neural Networks , 455-462.	inproceedings
Abstract: Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10, 000 classifications per second and achieves 1 % classification error for 8 objects with views accumulated over 90 ∘ of 2D pose.
BibTeX: @inproceedings{GhoshSiyiEtAl-2016, author = {Ghosh, Rohan and Siyi, Tang and Rasouli, Mahdi and Thakor, Nitish V and Kukreja, Sunil L}, title = {Pose-invariant object recognition for event-based vision with slow-{ELM}}, booktitle = {International Conference on Artificial Neural Networks}, year = {2016}, pages = {455--462}, url = {http://link.springer.com/chapter/10.1007/978-3-319-44781-0_54}, doi = {http://doi.org/10.1007/978-3-319-44781-0_54} }
Goerg, G.M.	2013	Forecastable component analysis (ForeCA) [Abstract] [BibTeX] [URL]	e-print arXiv:1205.4591v3 .	misc
Abstract: I introduce Forecastable Component Analysis (ForeCA), a novel dimension reduction technique for temporally dependent signals. Based on a new forecastability measure, ForeCA finds an optimal transformation to separate a multivariate time series into a forecastable and an orthogonal white noise space. I present a converging algorithm with a fast eigenvector solution. Applications to financial and macro-economic time series show that ForeCA can successfully discover informative structure, which can be used for forecasting as well as classification. The R package ForeCA (this http URL) accompanies this work and is publicly available on CRAN.
BibTeX: @misc{Goerg-2013, author = {Goerg, Georg M}, title = {Forecastable component analysis ({ForeCA})}, year = {2013}, howpublished = {e-print arXiv:1205.4591v3}, url = {https://arxiv.org/abs/1205.4591v3} }
Goerg, G.M.	2013	Forecastable component analysis. [Abstract] [BibTeX] [URL]	ICML (2) , 64-72.	inproceedings
Abstract: I introduce Forecastable Component Analysis (ForeCA), a novel dimension re- duction technique for temporally dependent signals. Based on a new forecastability measure, ForeCA finds an optimal transfor- mation to separate a multivariate time series into a forecastable and an orthogonal white noise space. I present a converging algorithm with a fast eigenvector solution. Applica- tions to financial and macro-economic time series show that ForeCA can successfully discover informative structure, which can be used for forecasting as well as classification. The R package ForeCA accompanies this work and is publicly available on CRAN.
BibTeX: @inproceedings{Goerg-2013a, author = {Goerg, Georg M}, title = {Forecastable component analysis.}, booktitle = {ICML (2)}, year = {2013}, pages = {64--72}, url = {https://pdfs.semanticscholar.org/5be4/060e644b3fa1a6ac967e0f186b9fa3497899.pdf} }
Grathwohl, W. & Wilson, A.	2016	Disentangling space and time in video with hierarchical variational auto-encoders [Abstract] [BibTeX] [URL]	e-print arXiv:1612.04440 .	misc
Abstract: There are many forms of feature information present in video data. Principle among them are object identity infor- mation which is largely static across multiple video frames, and object pose and style information which continuously transforms from frame to frame. Most existing models con- found these two types of representation by mapping them to a shared feature space. In this paper we propose a probabilistic approach for learning separable representa- tions of object identity and pose information using unsu- pervised video data. Our approach leverages a deep gen- erative model with a factored prior distribution that en- codes properties of temporal invariances in the hidden fea- ture set. Learning is achieved via variational inference. We present results of learning identity and pose informa- tion on a dataset of moving characters as well as a dataset of rotating 3D objects. Our experimental results demon- strate our model’s success in factoring its representation, and demonstrate that the model achieves improved perfor- mance in transfer learning tasks.
BibTeX: @misc{GrathwohlWilson-2016, author = {Grathwohl, Will and Wilson, Aaron}, title = {Disentangling space and time in video with hierarchical variational auto-encoders}, year = {2016}, howpublished = {e-print arXiv:1612.04440}, url = {https://arxiv.org/pdf/1612.04440.pdf} }
Gregor, K. & LeCun, Y.	2010	Emergence of complex-like cells in a temporal product network with local receptive fields [Abstract] [BibTeX] [URL] [URL(2)]	e-print arXiv:1006.0448 .	misc
Abstract: We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that represents the content of the image, constrained to be constant over several consecutive frames, and one that represents the precise location of features, which is allowed to vary over time but constrained to be sparse. The architecture uses an encoder to extract features, and a decoder to reconstruct the input from the features. The method was applied to patches extracted from consecutive movie frames and produces orientation and frequency selective units analogous to the complex cells in V1. An extension of the method is proposed to train a network composed of units with local receptive field spread over a large image of arbitrary size. A layer of complex cells, subject to sparsity constraints, pool feature units over overlapping local neighborhoods, which causes the feature units to organize themselves into pinwheel patterns of orientation-selective receptive fields, similar to those observed in the mammalian visual cortex. A feed-forward encoder efficiently computes the feature representation of full images.
BibTeX: @misc{GregorLeCun-2010, author = {Gregor, Karo and LeCun, Yann}, title = {Emergence of complex-like cells in a temporal product network with local receptive fields}, year = {2010}, howpublished = {e-print arXiv:1006.0448}, url = {https://arxiv.org/abs/1006.0448}, url2 = {https://pdfs.semanticscholar.org/31f0/4f8f83365fabf7ba9c9be1179c0da6815128.pdf} }
Grünewälder, S.	2009	Application of statistical estimation theory, adaptive sensory systems and time series processing to reinforcement learning [BibTeX] [URL]	Fakultät IV-Elektrotechnik und Informatik, Technische Universität Berlin, Fakultät IV-Elektrotechnik und Informatik, Technische Universität Berlin .	phdthesis
BibTeX: @phdthesis{Gruenewaelder-2009, author = {Gr{\"u}new{\"a}lder, Steffen}, title = {Application of statistical estimation theory, adaptive sensory systems and time series processing to reinforcement learning}, school = {Fakult{\"{a}}t IV-Elektrotechnik und Informatik, Technische Universit{\"{a}}t Berlin}, year = {2009}, url = {https://www.deutsche-digitale-bibliothek.de/binary/6Z7DL3XYO7BSFNSVAOKVOQE45HNN23J7/full/1.pdf} }
Gu, S.; Liu, Y.; Zhang, N. & Du, D.	2015	Fault detection approach based on weighted principal component analysis applied to continuous stirred tank reactor [Abstract] [BibTeX] [URL]	The Open Mechanical Engineering Journal , 9, 966-972.	article
Abstract: Fault detection approach based on principal component analysis (PCA) may perform not well when the process is time-varying, because it can cause unfavorable influence on feature extraction. To solve this problem, a modified PCA which considering variance maximization is proposed, referred to as weighted PCA (WPCA). WPCA can obtain the slow features information of observed data in time-varying system. The monitoring statistical indices are based on WPCA model and their confidence limits are computed by kernel density estimation (KDE). A simulation example on continuous stirred tank reactor (CSTR) show that the proposed method achieves better performance from the perspective of both fault detection rate and fault detection time than conventional PCA model.
BibTeX: @article{GuLiuEtAl-2015, author = {Gu, Shanmao and Liu, Yunlong and Zhang, Ni and Du, De}, title = {Fault detection approach based on weighted principal component analysis applied to continuous stirred tank reactor}, journal = {The Open Mechanical Engineering Journal}, year = {2015}, volume = {9}, pages = {966--972}, url = {https://benthamopen.com/contents/pdf/TOMEJ/TOMEJ-9-966.pdf}, doi = {http://doi.org/10.2174/1874155x01509010966} }
Gu, X.; Liu, C. & Wang, S.	2013	Supervised slow feature analysis for face recognition [Abstract] [BibTeX] [URL]	Biometric Recognition , Lecture Notes in Computer Science , 8232, 178-184. Eds. Sun, Z.; Shan, S.; Yang, G.; Zhou, J.; Wang, Y. & Yin, Y. Publ. Springer International Publishing.	incollection
Abstract: Slow feature analysis (SFA) is a new method based on the slowness principle and extracts slowly varying signals out of the input data. However, traditional SFA cannot be directly performed on those dataset without an obvious temporal structure. In this paper, a novel supervised slow feature analysis (SSFA) is proposed, which constructs pseudo-time series by taking advantage of the consensus information. Extensive experiments on AR and PIE face databases demonstrate superiority of our proposed method.
BibTeX: @incollection{GuLiuEtAl-2013, author = {Gu, Xingjian and Liu, Chuancai and Wang, Sheng}, title = {Supervised slow feature analysis for face recognition}, booktitle = {Biometric Recognition}, publisher = {Springer International Publishing}, year = {2013}, volume = {8232}, pages = {178--184}, url = {http://link.springer.com/chapter/10.1007/978-3-319-02961-0_22}, doi = {http://doi.org/10.1007/978-3-319-02961-0_22} }
Gu, X.; Liu, C. & Wang, S.	2015	Adaptive unsupervised slow feature analysis for feature extraction [Abstract] [BibTeX] [URL] [URL(2)]	Journal of Electronic Imaging , 24(2), 023021-023021. Publ. International Society for Optics and Photonics.	article
Abstract: Slow feature analysis (SFA) extracts slowly varying features out of the input data and has been successfully applied on pattern recognition. However, SFA heavily relies on the constructed time series when SFA is applied on databases that neither have obvious temporal structure nor have label information. Traditional SFA constructs time series based on k-nearest neighborhood (k-NN) criterion. Specifically, the time series set constructed by k-NN criterion is likely to include noisy time series or lose suitable time series because the parameter k is difficult to determine. To overcome these problems, a method called adaptive unsupervised slow feature analysis (AUSFA) is proposed. First, AUSFA designs an adaptive criterion to generate time series for characterizing submanifold. The constructed time series have two properties: (1) two points of time series lie on the same submanifold and (2) the submanifold of the time series is smooth. Second, AUSFA seeks projections that simultaneously minimize the slowness scatter and maximize the fastness scatter to extract slow discriminant features. Extensive experimental results on three benchmark face databases demonstrate the effectiveness of our proposed method.
BibTeX: @article{GuLiuEtAl-2015a, author = {Gu, Xingjian and Liu, Chuancai and Wang, Sheng}, title = {Adaptive unsupervised slow feature analysis for feature extraction}, journal = {Journal of Electronic Imaging}, publisher = {International Society for Optics and Photonics}, year = {2015}, volume = {24}, number = {2}, pages = {023021--023021}, url = {http://electronicimaging.spiedigitallibrary.org/article.aspx?articleid=2213384}, url2 = {https://www.researchgate.net/profile/Chuancai_Liu3/publication/277594831_Adaptive_unsupervised_slow_feature_analysis_for_feature_extraction/links/5571056108aef8e8dc632db5.pdf}, doi = {http://doi.org/10.1117/1.jei.24.2.023021} }
Gu, X.; Liu, C.; Wang, S. & Zhao, C.	2015	Feature extraction using adaptive slow feature discriminant analysis [Abstract] [BibTeX] [URL] [URL(2)]	Neurocomputing , 154, 139-148.	article
Abstract: Slow feature discriminant analysis (SFDA) is an attractive biologically inspired learning method to extract discriminant features for classification. However, SFDA\ heavily relies on the constructed time series. For discriminant analysis, SFDA\ cannot make full use of discriminant power for classification, because the type of data distribution is unknown. To address those problems, we propose a new feature extraction method called adaptive slow feature discriminant analysis (ASFDA) in this paper. First, we design a new adaptive criterion to generate within-class time series. The time series have two properties: (1) a pair of time series lies on the same sub-manifold, (2) the sub-manifold of a pair of time series is smooth. Second, ASFDA\ seeks projections to minimize within-class temporal variation and maximize between-class temporal variation simultaneously based on maximum margin criterion. ASFDA\ provides an adaptive parameter to balance between-class temporal variation and within-class temporal variation to obtain an optimal discriminant subspace. Experimental results on three benchmark face databases demonstrate that our proposed ASFDA\ is superior to some state-of-the-art methods.
BibTeX: @article{GuLiuEtAl-2015b, author = {Xingjian Gu and Chuancai Liu and Sheng Wang and Cairong Zhao}, title = {Feature extraction using adaptive slow feature discriminant analysis}, journal = {Neurocomputing}, year = {2015}, volume = {154}, pages = {139--148}, url = {http://www.sciencedirect.com/science/article/pii/S0925231214016749}, url2 = {https://www.researchgate.net/profile/Chuancai_Liu3/publication/272102390_Feature_extraction_using_adaptive_slow_feature_discriminant_analysis/links/55701db508aec226830ac10f.pdf}, doi = {http://doi.org/10.1016/j.neucom.2014.12.010} }
Gu, X.; Liu, C.; Wang, S.; Zhao, C. & Wu, S.	2015	Uncorrelated slow feature discriminant analysis using globality preserving projections for feature extraction [Abstract] [BibTeX] [URL]	Neurocomputing , 168, 488-499.	article
Abstract: Slow Feature Discriminant Analysis (SFDA) is a supervised feature extraction method for classification inspired by biological mechanism. However, SFDA\ only considers the local geometrical structure information of data and ignores the global geometrical structure information. Furthermore, previous works have demonstrated that uncorrelated features of minimum redundancy are effective for classification. In this paper, a novel method called uncorrelated slow feature discriminant analysis using globality preserving projections (USFDA-GP) is proposed for feature extraction and recognition. In USFDA-GP, two kinds of global information are imposed to the objective function of conventional SFDA\ for respecting some more global geometric structures. We also provide an analytical solution by simple eigenvalue decomposition to the optimal model instead of previous iterative method. Experimental results on Extended YaleB, CMU\ PIE\ and LFW-a face databases demonstrate the effectiveness of our proposed method.
BibTeX: @article{GuLiuEtAl-2015c, author = {Xingjian Gu and Chuancai Liu and Sheng Wang and Cairong Zhao and Songsong Wu}, title = {Uncorrelated slow feature discriminant analysis using globality preserving projections for feature extraction}, journal = {Neurocomputing}, year = {2015}, volume = {168}, pages = {488--499}, url = {http://www.sciencedirect.com/science/article/pii/S0925231215007778}, doi = {http://doi.org/10.1016/j.neucom.2015.05.079} }
Gu, X.; Liu, C. & Yang, Z.	2014	Dimensionality reduction based on supervised slow feature analysis for face recognition [Abstract] [BibTeX] [URL]	structure , 7(1). Publ. Citeseer.	article
Abstract: Slow feature analysis (SFA) is motivated by biological model to extracts slowly varying feature from a quickly varying input signal. However, traditional slow feature analysis is an unsupervised method to extract slow or invariant feature and cannot be directly applied on the data set without an obvious temporal structure, i.e. face databases. In this paper, we propose a supervised slow feature analysis to do dimensionality reduction for face recognition. First, a new criterion is developed to construct a Pseudo-time series for data sets without an obvious temporal structure. Then, the first-order derivative at each point in the Pseudo-time series is computed in form of vectors. At last we construct the objective function of SSFA that ensures the secondary moment of first-order derivative as small as possible in the embedding space. SSFA is able to extract the invariant feature for each class and preserve the local structure in embedding space simultaneously. Experimental results on the Yale, ORL, AR, and FERET face databases show the effectiveness of the proposed algorithm.
BibTeX: @article{GuLiuEtAl-2014, author = {Gu, Xingjian and Liu, Chuancai and Yang, Zhangjing}, title = {Dimensionality reduction based on supervised slow feature analysis for face recognition}, journal = {structure}, publisher = {Citeseer}, year = {2014}, volume = {7}, number = {1}, url = {http://www.sersc.org/journals/IJSIP/vol7_no1/2.pdf}, doi = {http://doi.org/10.14257/ijsip.2014.7.1.02} }
Gu, X.; Shu, X.; Ren, S. & Xu, H.	2018	Two Dimensional Slow Feature Discriminant Analysis via L 2, 1 Norm Minimization for Feature Extraction. [BibTeX]	KSII Transactions on Internet & Information Systems , 12(7).	article
BibTeX: @article{GuShuEtAl-2018, author = {Gu, Xingjian and Shu, Xiangbo and Ren, Shougang and Xu, Huanliang}, title = {Two Dimensional Slow Feature Discriminant Analysis via L 2, 1 Norm Minimization for Feature Extraction.}, journal = {KSII Transactions on Internet \& Information Systems}, year = {2018}, volume = {12}, number = {7}, doi = {http://doi.org/10.3837/tiis.2018.07.012} }
Guo, F.; Shang, C.; Huang, B.; Wang, K.; Yang, F. & Huang, D.	2016	Monitoring of operating point and process dynamics via probabilistic slow feature analysis [Abstract] [BibTeX] [URL]	Chemometrics and Intelligent Laboratory Systems , 151, 115-125. Publ. Elsevier.	article
Abstract: Traditional multivariate statistical process monitoring (MSPM) approaches aim at detecting deviations from the routine operating condition. However, if the process remains well controlled by feedback controllers in spite of some deviations, alarms triggered in this context become no longer necessary. In this regard, slow feature analysis (SFA) has been recently applied to MSPM tasks by Shang et al. (2015), which allows for seperate distributions of both nominal operating points and dynamic behaviors. Since a poor control performance is always characterized by dynamics anomalies, one can discriminate nominal operating deviations with acceptable control performance, from real faults that deserve more attentions, according to the temporal dynamics of processes. In this work, we propose a new process monitoring scheme based upon probabilistic SFA (PSFA). Compared to deterministic SFA, its probabilistic extension takes the measurement noise into considerations and allows for missing data imputation conveniently, which is beneficial for process monitoring. Apart from generic T2 and SPE metrics for monitoring the operating point, a novel S2 statistics is considered for exclusively monitoring temporal behaviors of processes. Two case studies are provided to show the efficacy of the proposed monitoring approach.
BibTeX: @article{GuoShangEtAl-2016, author = {Guo, Feihong and Shang, Chao and Huang, Biao and Wang, Kangcheng and Yang, Fan and Huang, Dexian}, title = {Monitoring of operating point and process dynamics via probabilistic slow feature analysis}, journal = {Chemometrics and Intelligent Laboratory Systems}, publisher = {Elsevier}, year = {2016}, volume = {151}, pages = {115--125}, url = {http://www.sciencedirect.com/science/article/pii/S0169743915003329}, doi = {http://doi.org/10.1016/j.chemolab.2015.12.017} }
Ha Quang, M. & Wiskott, L.	2011	Slow feature analysis and decorrelation filtering for separating correlated sources [Abstract] [BibTeX] [URL]	Proc. 13^th International Conference on Computer Vision (ICCV), Nov 6-13, Barcelona, Spain , 866-873. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: We generalize the method of Slow Feature Analysis for vector-valued functions of multivariables and apply it to the problem of blind source separation, in particular image separation. For the linear case, exact mathematical analysis is given, which shows in particular that the sources are perfectly separated by SFA if and only if they and their first order derivatives are uncorrelated. When the sources are correlated, we apply the following technique called decorrelation filtering: use a linear filter to decorrelate the sources and their derivatives, then apply the separating matrix obtained on the filtered sources to the original sources. We show that if the filtered sources are perfectly separated by this matrix, then so are the original sources. We show how to numerically obtain such a decorrelation filter by solving a nonlinear optimization problem. This technique can also be applied to other linear separation methods, whose output signals are decorrelated, such as ICA.
BibTeX: @inproceedings{HaQuangWiskott-2011, author = {Ha Quang, Minh and Wiskott, L.}, title = {Slow feature analysis and decorrelation filtering for separating correlated sources}, booktitle = {Proc.\ 13\textsuperscript{th} International Conference on Computer Vision (ICCV), Nov 6-13, Barcelona, Spain}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {866--873}, url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6126327&abstractAccess=no&userType=inst}, doi = {http://doi.org/10.1109/ICCV.2011.6126327} }
Ha Quang, M. & Wiskott, L.	2013	Multivariate slow feature analysis and decorrelation filtering for blind source separation [Abstract] [BibTeX] [URL]	IEEE Trans. on Image Processing , 22(7), 2737-2750.	article
Abstract: We generalize the method of Slow Feature Analysis (SFA) for vector-valued functions of several variables and apply it to the problem of blind source separation, in particular to image separation. It is generally necessary to use multivariate SFA instead of univariate SFA for separating multi-dimensional signals. For the linear case, an exact mathematical analysis is given, which shows in particular that the sources are perfectly separated by SFA if and only if they and their first order derivatives are uncorrelated. When the sources are correlated, we apply the following technique called decorrelation filtering: use a linear filter to decorrelate the sources and their derivatives in the given mixture, then apply the unmixing matrix obtained on the filtered mixtures to the original mixtures. If the filtered sources are perfectly separated by this matrix, so are the original sources. A decorrelation filter can be numerically obtained by solving a nonlinear optimization problem. This technique can also be applied to other linear separation methods, whose output signals are decorrelated, such as ICA. When there are more mixtures than sources, one can determine the actual number of sources by using a regularized version of SFA with decorrelation filtering. Extensive numerical experiments using SFA and ICA with decorrelation filtering, supported by mathematical analysis, demonstrate the potential of our methods for solving problems involving blind source separation.
BibTeX: @article{HaQuangWiskott-2013, author = {Ha Quang, Minh and Wiskott, L.}, title = {Multivariate slow feature analysis and decorrelation filtering for blind source separation}, journal = {IEEE Trans.\ on Image Processing}, year = {2013}, volume = {22}, number = {7}, pages = {2737--2750}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6497610}, doi = {http://doi.org/10.1109/TIP.2013.2257808} }
Hang, C.; Liu, W. & Wangcai, C.	2019	New magnetic Barkhausen noise feature extraction for stress detection with slow feature analysis [BibTeX] [URL(2)]	Insight - Non-Destructive Testing and Condition Monitoring , 61, 395-403.	article
BibTeX: @article{article, author = {Hang, Cheng and Liu, Wenbo and Wangcai, Chen}, title = {New magnetic Barkhausen noise feature extraction for stress detection with slow feature analysis}, journal = {Insight - Non-Destructive Testing and Condition Monitoring}, year = {2019}, volume = {61}, pages = {395-403}, url2 = {https://www.researchgate.net/publication/334322213_New_magnetic_Barkhausen_noise_feature_extraction_for_stress_detection_with_slow_feature_analysis}, doi = {http://doi.org/10.1784/insi.2019.61.7.395} }
Hansard, M. & Horaud, R.	2010	Complex cells and the representation of local image-structure [Abstract] [BibTeX] [URL] [URL(2)]	RR-7485, INRIA. 2010Research Report, INRIA, INRIA (RR-7485, inria-00546779).	techreport
Abstract: The receptive fields of simple cells in the visual cortex can be un- derstood as linear filters. These filters can be modelled by Gabor functions, or by Gaussian derivatives. Gabor functions can also be combined in an ‘en- ergy model’ of the complex cell response. This paper proposes an alternative model of the complex cell, based on Gaussian derivatives. It is most important to account for the insensitivity of the complex response to small shifts of the image. The new model uses a linear combination of the first few derivative filters, at a single position, to approximate the first derivative filter, at a series of adjacent positions. The maximum response, over all positions, gives a signal that is insensitive to small shifts of the image. This model, unlike previous ap- proaches, is based on the scale space theory of visual processing. In particular, the complex cell is built from filters that respond to the 2-d differential struc- ture of the image. The computational aspects of the new model are studied in one and two dimensions, using the steerability of the Gaussian derivatives. The response of the model to basic images, such as edges and gratings, is derived formally. The response to natural images is also evaluated, using statistical measures of shift insensitivity. The relevance of the new model to the cortical image representation is discussed
BibTeX: @techreport{HansardHoraud-2010, author = {Miles Hansard and Radu Horaud}, title = {Complex cells and the representation of local image-structure}, school = {INRIA}, year = {2010}, number = {RR-7485, inria-00546779}, url = {https://hal.inria.fr/inria-00546779/file/RR-7485.pdf}, url2 = {https://pdfs.semanticscholar.org/3838/031546a0a61a1600b5e3b8316413e13ae7a6.pdf} }
Hansard, M. & Horaud, R.	2011	A differential model of the complex cell [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 23(9), 2324-2357. Publ. MIT Press - Journals.	article
Abstract: The receptive fields of simple cells in the visual cortex can be understood as linear filters. These filters can be modelled by Gabor functions, or by Gaussian derivatives. Gabor functions can also be combined in an ‘energy model’ of the complex cell response. This paper proposes an alternative model of the complex cell, based on Gaussian derivatives. It is most important to account for the insensitivity of the complex response to small shifts of the image. The new model uses a linear combination of the first few derivative filters, at a single position, to approximate the first derivative filter, at a series of adjacent positions. The maximum response, over all positions, gives a signal that is insensitive to small shifts of the image. This model, unlike previous approaches, is based on the scale space theory of visual processing. In particular, the complex cell is built from filters that respond to the 2-D differential structure of the image. The computational aspects of the new model are studied in one and two dimensions, using the steerability of the Gaussian derivatives. The response of the model to basic images, such as edges and gratings, is derived formally. The response to natural images is also evaluated, using statistical measures of shift insensitivity. The neural implementation and predictions of the model are discussed.
BibTeX: @article{HansardHoraud-2011, author = {Hansard, Miles and Horaud, Radu}, title = {A differential model of the complex cell}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2011}, volume = {23}, number = {9}, pages = {2324--2357}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00163}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.225.7084&rep=rep1&type=pdf}, doi = {http://doi.org/10.1162/neco_a_00163} }
Hanyuan, Z. & Xuemin, T.	2017	Batch process monitoring based on batch dynamic Kernel slow feature analysis [Abstract] [BibTeX] [URL]	2017 29th Chinese Control And Decision Conference (CCDC) , 4772-4777.	inproceedings
Abstract: The traditional nonlinear dynamic batch process monitoring approaches are unable to extract the underlying driving forces of batch process. In this paper, a novel batch process monitoring method based on batch dynamic kernel slow feature analysis (BDKSFA) is proposed not only to capture nonlinear and dynamic characteristics but also to extract the underlying driving forces. The three-way data matrix is first unfolded and normalized and then rearranged into three-way matrix again. In order to contain stochastic variations and deviations among batches, the total average kernel matrix is computed as an average of I batch average kernel matrixes, each of which is also an average of I kernel matrixes for each batch. Based on the slow features extracted from BDKSFA model, two monitoring statistics are constructed to detect batch process fault. The simulation results obtained from the benchmark fed-batch penicillin fermentation process demonstrate the superiority of the developed method in terms of fault detection performance.
BibTeX: @inproceedings{7979339, author = {Hanyuan, Zhang and Xuemin, Tian}, title = {Batch process monitoring based on batch dynamic Kernel slow feature analysis}, booktitle = {2017 29th Chinese Control And Decision Conference (CCDC)}, year = {2017}, pages = {4772-4777}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7979339}, doi = {http://doi.org/10.1109/CCDC.2017.7979339} }
Hao, T.; Wang, Q.; Wu, D. & Sun, J.	2017	Multiple person tracking based on slow feature analysis [Abstract] [BibTeX] [URL]	Multimedia Tools and Applications , 77, 3623-3637.	article
Abstract: Object tracking is one of the most important components in numerous applications of computer vision. However, it still has many challenges to be solved, such as occlusion, matching, data association, etc. In this paper, we proposed to utilize slow feature analysis (SFA) method to handle the multiple person tracking problem. First, the part-based model is utilized to detect pedestrian in each frame. Then, a set of reliable tracklets is generated by utilizing spatial-temporal information of detection results. Third, SFA method is leveraged to extract slow-feature for these reliable tracklets. Finally, the traditional graph matching method is utilized to handle data association problem and consequently generate the final trajectory for individual tracking object. Some popular datasets are used in this study. The extensive comparison experiments demonstrate the superiority of the proposed method.
BibTeX: @article{Hao2017MultiplePT, author = {Tong Hao and Qian Wang and Dan Wu and Jinsheng Sun}, title = {Multiple person tracking based on slow feature analysis}, journal = {Multimedia Tools and Applications}, year = {2017}, volume = {77}, pages = {3623-3637}, url = {https://link.springer.com/article/10.1007/s11042-017-5218-4} }
Harrison, M.; Geman, S. & Bienenstock, E.	2004	Using statistics of natural images to facilitate automatic receptive field analysis [BibTeX] [URL] [URL(2)]	techreport, Division of Applied Mathematics, Brown University, Providence, USA, Division of Applied Mathematics, Brown University, Providence, USA (APPTS Report \#04-2). Publ. Citeseer.	techreport
BibTeX: @techreport{HarrisonGemanEtAl-2004, author = {Harrison, Matthew and Geman, Stuart and Bienenstock, Elie}, title = {Using statistics of natural images to facilitate automatic receptive field analysis}, publisher = {Citeseer}, school = {Division of Applied Mathematics, Brown University, Providence, USA}, year = {2004}, number = {APPTS Report \#04-2}, url = {http://www.dam.brown.edu/ptg/REPORTS/04-2.pdf}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.58.807&rep=rep1&type=pdf} }
Hashimoto, W.	2003	Quadratic forms in natural images [Abstract] [BibTeX] [URL]	Network: Computation in Neural Systems , 14(4), 765-788. Publ. Taylor & Francis.	article
Abstract: Several studies have succeeded in correlating natural image statistics with receptive field properties of neurons in the primary visual cortex. If we determine the parameters of linear transformations that make their output values as independent as possible when input data are natural images, we obtain parameter values that correspond to simple cell characteristics. It was also proved that, by making output values as temporally coherent as possible, simple cell characteristics also emerge. However, complex cell properties have not been fully explained by previous studies of natural image statistics. In this study, we examine whether we could reproduce complex cell properties by determining the parameters of two-layer networks that make their outputs as independent and sparse as possible or as temporally coherent as possible. Input– output functions of two-layer networks correspond to quadratic forms and they form a class of functions that includes complex cell responses and many other functions. Therefore, we employed two-layer networks as a framework for discussing complex cell properties as in previous studies. By maximizing the independence and sparseness of output values of two-layer networks without considering the temporal structure of input images, squared responses of simple cells are obtained and complex cell properties are not reproduced. On the other hand, by maximizing the temporal coherence of output, we obtain complex cell properties among other kinds of input–output functions. In previous studies, the measure of temporal coherence was the squared difference between the responses to two consecutive input images. We obtain two-layer networks that minimize this measure and show that some of them exhibit properties of complex cells but not clearly. We propose the sparseness of difference between responses to two consecutive inputs as an alternative measure of temporal coherence. We formulate an algorithm to maximize the sparseness of difference and show that complex cell properties emerge more clearly.
BibTeX: @article{Hashimoto-2003, author = {Wakako Hashimoto}, title = {Quadratic forms in natural images}, journal = {Network: Computation in Neural Systems}, publisher = {Taylor \& Francis}, year = {2003}, volume = {14}, number = {4}, pages = {765--788}, url = {http://www.tandfonline.com/doi/abs/10.1088/0954-898X_14_4_308}, doi = {http://doi.org/10.1088/0954-898x/14/4/308} }
He, Y.; Jia, Z.; Yang, J. & Kasabov, N.K.	2021	Multispectral Image Change Detection Based on Single-Band Slow Feature Analysis [Abstract] [BibTeX] [URL]	Remote Sensing , 13(15).	article
Abstract: Due to differences in external imaging conditions, multispectral images taken at different periods are subject to radiation differences, which severely affect the detection accuracy. To solve this problem, a modified algorithm based on slow feature analysis is proposed for multispectral image change detection. First, single-band slow feature analysis is performed to process bitemporal multispectral images band by band. In this way, the differences between unchanged pixels in each pair of single-band images can be sufficiently suppressed to obtain multiple feature-difference images containing real change information. Then, the feature-difference images of each band are fused into a grayscale distance image using the Euclidean distance. After Gaussian filtering of the grayscale distance image, false detection points can be further reduced. Finally, the k-means clustering method is performed on the filtered grayscale distance image to obtain the binary change map. Experiments reveal that our proposed algorithm is less affected by radiation differences and has obvious advantages in time complexity and detection accuracy.
BibTeX: @article{rs13152969, author = {He, Youxi and Jia, Zhenhong and Yang, Jie and Kasabov, Nikola K.}, title = {Multispectral Image Change Detection Based on Single-Band Slow Feature Analysis}, journal = {Remote Sensing}, year = {2021}, volume = {13}, number = {15}, url = {https://www.mdpi.com/2072-4292/13/15/2969}, doi = {http://doi.org/10.3390/rs13152969} }
He, Z.; Li, X.; Zhang, Z.; Zhang, Y.; Xiao, J. & Zhou, X.	2016	Structure-aware slow feature analysis for age estimation [Abstract] [BibTeX] [URL]	IEEE Signal Processing Letters , 23(12), 1702-1706. Publ. IEEE.	article
Abstract: As an important and challenging problem in computer vision, face age estimation is typically cast as a classification or regression problem over a set of face samples. However, most existing efforts to age estimation usually cope with the face samples individually, which do not take full advantage of the temporal structure and contextual structure of the face samples. In this letter, we propose an age estimation approach named structure-aware slow feature analysis, which is capable of effectively capturing the structure of human faces in the aspects of time-related smoothness for progressive age variation as well as face-related attribute constraints for face age consistency. As a result, we present an iterative optimization scheme to effectively learn the slowly varying feature transformation. Experimental results demonstrate the effectiveness of our approach on the Morph dataset.
BibTeX: @article{HeLiEtAl-2016, author = {He, Zhouzhou and Li, Xi and Zhang, Zhongfei and Zhang, Yaqing and Xiao, Jun and Zhou, Xue}, title = {Structure-aware slow feature analysis for age estimation}, journal = {IEEE Signal Processing Letters}, publisher = {IEEE}, year = {2016}, volume = {23}, number = {12}, pages = {1702--1706}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7549096}, doi = {http://doi.org/10.1109/lsp.2016.2602538} }
Hein, K.	2009	Lernende Klassifikation beschleunigungsbasierter 3D-Gesten des Wii-Controllers [BibTeX] [URL]	Projektbericht, University of Applied Sciences Cologne, Gummersbach .	misc
BibTeX: @misc{Hein-2009, author = {Hein, Kristine}, title = {Lernende {K}lassifikation beschleunigungsbasierter {3D}-{G}esten des {W}ii-{C}ontrollers}, year = {2009}, howpublished = {Projektbericht, University of Applied Sciences Cologne, Gummersbach}, url = {http://maanvs03.gm.fh-koeln.de/webpub/CIOPReports.d/Hein10b.d/Klassifikation3D.pdf} }
Hein, K.	2010	Klassifizierung von beschleunigungsbasierten 3D-Gesten des Wii-Controllers [Abstract] [BibTeX] [URL]	Fachhochschule Köln, Campus Gummersbach, Fakultät für Informatik und Ingenieurwissenschaften, Fachhochschule Köln, Campus Gummersbach, Fakultät für Informatik und Ingenieurwissenschaften .	mastersthesis
Abstract: Diese Arbeit untersucht die Slow Feature Analysis (SFA) auf ihre Möglichkeiten zur Gestenerkennung auf Basis von gerätebasierten 3D-Beschleuningungsdaten des Wii- Controllers. Bisherige Ansätze zur Klassifizierung von beschleunigungsbasierten 3D-Gesten verwenden häufig ein HMM-basiertes Verfahren. Die Erkennung von Anfang und Ende einer Geste erfolgt in der Regel entweder anhand eines Ruhelage-Filters oder mit Hilfe von externen Markierungen der Gesten bei ihrer Erhebung. Hier soll nun ein anderer Ansatz, nämlich die Gestenerkennung mit der Slow Feature Analysis (SFA) vorgestellt, näher untersucht und mit anderen gängigen Verfahren verglichen werden. Die SFA ist ein Lernalgorithmus, der die am langsamsten variierenden Signale aus einem sich schnell ändernden Eingangssignal findet, und anhand dessen lernt auf die Gestenklassen zu schlieÿen. Die SFA wurde bereits erfolgreich zur Mustererkennung von handgeschriebene Ziffern eingesetzt und zeigt auch in diesem Ansatz für die Gestenerkennung vergleichbare Ergebnisse mit anderen gängigen Klassifizierungsverfahren. Zur Segmentierung eines Gestensignal um Anfangs- und Endpunkt einer Geste zu ermitteln, wurden unterschiedliche Varianten mit der SFA und ein anderer alternativer regelbasierter Ansatz untersucht. Diese lieferten vergleichbare Ergebnisse mit einem gängigen dynamischen Segmentierungsverfahren.
BibTeX: @mastersthesis{Hein-2010, author = {Kristine Hein}, title = {{K}lassifizierung von beschleunigungsbasierten 3{D-G}esten des {W}ii-{C}ontrollers}, school = {Fachhochschule K{\"{o}}ln, Campus Gummersbach, Fakult{\"{a}}t f{\"{u}}r Informatik und Ingenieurwissenschaften}, year = {2010}, url = {https://epb.bibl.th-koeln.de/files/236/Masterthesis_final.pdf} }
Hein, K.	2011	Gestenerkennung mit der SFA: Klassifizierung von beschleunigungsbasierten 3D-Gesten des Wii-Controllers [Abstract] [BibTeX]	Köln, Fachhochsch., Masterarbeit, 2010, Köln, Fachhochsch., Masterarbeit, 2010 .	mastersthesis
Abstract: Diese Arbeit untersucht die Slow Feature Analysis (SFA) auf ihre Möglichkeiten zur Gestenerkennung auf Basis von gerätebasierten 3D-Beschleuningungsdaten des Wii-Controllers. Bisherige Ansätze zur Klassifizierung von beschleunigungsbasierten 3D-Gesten verwenden häfig ein HMM-basiertes Verfahren. Die Erkennung von Anfang und Ende einer Geste erfolgt in der Regel entweder anhand eines Ruhelage-Filters oder mit Hilfe von externen Markierungen der Gesten bei ihrer Erhebung. Hier soll nun ein anderer Ansatz, nämlich die Gestenerkennung mit der Slow Feature Analysis (SFA) vorgestellt, näher untersucht und mit anderen gängigen Verfahren verglichen werden. Die SFA ist ein Lernalgorithmus, der die am langsamsten variierenden Signale aus einem sich schnell ändernden Eingangssignal findet, und anhand dessen lernt auf die Gestenklassen zu schließen. Die SFA wurde bereits erfolgreich zur Mustererkennung von handgeschriebenen Ziffern eingesetzt und zeigt auch in diesem Ansatz für die Gestenerkennung vergleichbare Ergebnisse mit anderen gängigen Klassifizierungsverfahren. Zur Segmentierung eines Gestensignal um Anfangs- und Endpunkt einer Geste zu ermitteln, wurden unterschiedliche Varianten mit der SFA und ein anderer alternativer regelbasierter Ansatz untersucht. Diese lieferten vergleichbare Ergebnisse mit einem gängigen dynamischen Segmentierungsverfahren.
BibTeX: @mastersthesis{Hein-2011, author = {Hein, Kristine}, title = {Gestenerkennung mit der {SFA}: {K}lassifizierung von beschleunigungsbasierten {3D}-{G}esten des {W}ii-{C}ontrollers}, school = {K{\"o}ln, Fachhochsch., Masterarbeit, 2010}, year = {2011} }
Hinze, C.	2012	Optimale Stimuli in einem hierarchischen SFA-Netzwerk. [BibTeX] [URL(2)]	Klinik für Neurologie der Charité Berlin, Institut für theoretische Biologie der Humboldt Universität Berlin, Klinik für Neurologie der Charité Berlin, Institut für theoretische Biologie der Humboldt Universität Berlin .	phdthesis
BibTeX: @phdthesis{Hinze-2012, author = {Christian Hinze}, title = {Optimale {S}timuli in einem hierarchischen {SFA}-{N}etzwerk.}, school = {Klinik f{\"{u}}r Neurologie der Charit{\'{e}} Berlin, Institut f{\"{u}}r theoretische Biologie der Humboldt Universit{\"{a}}t Berlin}, year = {2012}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Hinze-2012-Doktorarbeit.pdf} }
Hinze, C.; Wilbert, N. & Wiskott, L.	2009	Visualization of higher-level receptive fields in a hierarchical model of the visual system. [Abstract] [BibTeX] [URL] [URL(3)]	Proc. 18^th Annual Computational Neuroscience Meeting (CNS'09), July 18-23, Berlin, Germany .	inproceedings
Abstract: Early visual receptive fields have been measured extensively and are fairly well mapped. Receptive fields in higher areas, on the other hand, are very difficult to characterize, because it is not clear what they are tuned to and which stimuli to use to study them. Early visual receptive fields have been reproduced by computational models. Slow feature analysis (SFA), for instance, is an algorithm that finds functions that extract most slowly varying features from a multi-dimensional input sequence [1]. Applied to quasi-natural image sequences, i.e. image sequences derived from natural images by translation, rotation and zoom, SFA yields many properties of complex cells in V1 [2]. A hierarchical network of SFA units learns invariant object representations much like in IT [3]. These successes suggest that units of intermediate layers in the network might share properties with cells in V2 or V4. The goal of this project is therefore to develop techniques to visualize and characterize such units to understand how cells in V2/V4 might work. This is nontrivial because the units are highly nonlinear. The algorithm is gradient-based and applied in a cascade within the network. We start with a natural image patch as an input, which then gets optimized by gradient ascent to maximize the output of one particular unit. Figure 1 shows such optimal stimuli for units in the first (a, b) and the second layer (c, d). The latter can be associated with cells in V2/V4. We plan to extend this to higher layers and larger receptive fields and will also develop techniques to visualize the invariances of the units, i.e. those variations to the input that have little effect on the unit's output. The long-term goal is to provide a good stimulus set for characterizing cells in V2/V4. [Figure] Figure 1. Optimal stimuli of units in the first layer (a, b) and the second layer (c, d) of a hierarchical SFA network optimized for slowness and trained with quasi-natural image sequences. References 1. Wiskott L, Sejnowski TJ: Slow feature analysis: Unsupervised learning of invariances. Neural Computation 2002, 14:715-770. 2. Berkes P, Wiskott L: Slow feature analysis yields a rich repertoire of complex cell properties. J Vision 2005, 5:579-602. 3. Franzius M, Wilbert N, Wiskott L: Invariant object recognition with slow feature analysis. Proc 18^th Int'l Conf on Artificial Neural Networks 2008, 961-970.
BibTeX: @inproceedings{HinzeWilbertEtAl-2009, author = {Christian Hinze and Niko Wilbert and Laurenz Wiskott}, title = {Visualization of higher-level receptive fields in a hierarchical model of the visual system.}, booktitle = {Proc.\ 18\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'09), July 18--23, Berlin, Germany}, year = {2009}, url = {http://www.biomedcentral.com/1471-2202/10/S1/P158}, url3 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/HinzeWilbertEtAl-2009-ProcCNSBerlin-Poster-HigherRFs.pdf}, doi = {http://doi.org/10.1186/1471-2202-10-S1-P158} }
Höfer, S.	2009	Analyse des Laufverhaltens von humanoiden Robotern mit der Slow Feature Analysis [Abstract] [BibTeX] [URL(2)]	Studienarbeit, Humboldt-Universität zu Berlin, Institut für Informatik .	misc
Abstract: Die Slow Feature Analysis (SFA) ist ein Lernverfahren, welches sich langsam verän- dernde Komponenten aus einem mehrdimensionalen Eingabesignal extrahiert. Sie findet eine Eingabe-Ausgabe-Funktion, die es erlaubt, aus dem Eingabesignal mehrere ihrer Langsamkeit nach geordnete, unkorrelierte Komponenten zu berechnen. Diese Eingabe- Ausgabe-Funktion kann offline berechnet werden und liefert die langsamsten Komponen- ten, welche die optimale Lösung innerhalb einer eingeschränkten Familie von Funktionen darstellen. In der Regel kann bei geeigneter Wahl von Trainingsdaten diese Eingabe- Ausgabe-Funktion auch auf unbekannten Testdaten annähernd optimale Ergebnisse lie- fern und das Verfahren somit online nutzbar gemacht werden. Die SFA wird auf Beschleunigungssensordaten einer humanoiden Roboterserie ange- wandt, um Informationen über den aktuellen Zustand des Roboters zu gewinnen. Dabei geht es vor allem darum, für ein bestimmtes Laufmuster mit der SFA eine Komponente zu extrahieren, welche dem Roboter als Indikator dienen kann, sobald er droht das Gleichge- wicht zu verlieren und umzufallen. Zuerst werden verschiedene Anwendungsmöglichkeiten der SFA evaluiert und auf den gleichen Daten gelernt und getestet. Die gefundenen Kom- ponenten werden vorgestellt und interpretiert, darunter einige Komponenten, die sich als Kandidaten für eine Umfalldetektion eignen. Dann werden die von der SFA gelernten Eingabe-Ausgabe-Funktionen auch auf unbekannte Testdaten des gleichen sowie ande- rer Modelle derselben Roboterfamilie angewandt. Die Analyse zeigt, dass die gelernten Parameter in Abhängigkeit von den Trainingsdaten teilweise robust genug sind, um zu generalisieren und auf anderen Robotern gleicher Bauart als Umfalldetektion zu dienen.
BibTeX: @misc{Hoefer-2009, author = {H{\"o}fer, Sebastian}, title = {Analyse des {L}aufverhaltens von humanoiden {R}obotern mit der {S}low {F}eature {A}nalysis}, year = {2009}, howpublished = {Studienarbeit, Humboldt-Universit{\"{a}}t zu Berlin, Institut f{\"{u}}r Informatik}, url2 = {http://www.neurorobotik.de/downloads/publications/2009%20Ho%CC%88fer%20-%20Analyse%20des%20Laufverhaltens%20mit%20der%20Slowe%20Feature%20Analysis.pdf} }
Höfer, S.	2010	Anwendungen der slow feature analysis in der humanoiden robotik [Abstract] [BibTeX] [URL(2)]	Diploma Thesis Humboldt University of Berlin, Humboldt University of Berlin , Anwendungen der Slow Feature Analysis in der humanoiden Robotik . , Germany	mastersthesis
Abstract: This thesis deals with the Slow Feature Analysis (SFA), an unsupervised learning method stemming from the domain of theoretical biology, and its application in humanoid robotics. SFA is an algorithm that extracts abstract semantic features from a vectorial input signal. It is investigated which features SFA learns from proprioceptive, non-visual sensory data from a humanoid robot, and how the extracted features can be used for the robot’s self-perception and control. The thesis is divided into a theoretical and a practical part. The theoretical part describes the SFA algorithm and methods for the analysis of its results. Moreover, extensions and its relation to other methods are presented. The execution step of the SFA algorithm is reformulated in terms of an artificial neural model and optimised with respect to this model. In the practical part, two applications of SFA for a humanoid robot platform are presented. First, SFA is employed for the detection of static postures performed by the robot, as well as for dimensionality reduction of the sensory state space. The obtained results are compared to other methods for dimensionality reduction. Secondly, SFA is applied to a dynamic motion, more precisely, to a biped gait pattern. It is shown that SFA can be used within the sensorimotor loop that generates the gait pattern, while at the same time increasing the reactivity of the gait pattern without profound loss in stability.
BibTeX: @mastersthesis{Hoefer-2010, author = {Sebastian H{\"{o}}fer}, title = {Anwendungen der slow feature analysis in der humanoiden robotik}, booktitle = {Diploma Thesis}, school = {Humboldt University of Berlin}, year = {2010}, url2 = {http://www.sebastianhoefer.de/publications/Hoefer-SFA-Thesis.pdf} }
Höfer, S. & Hild, M.	2010	Using slow feature analysis to improve the reactivity of a humanoid robot's sensorimotor gait pattern [Abstract] [BibTeX] [URL] [URL(2)]	Proceedings of the International Conference on Fuzzy Computation and 2^nd International Conference on Neural Computation , Using Slow Feature Analysis to Improve the Reactivity of a Humanoid Robot's Sensorimotor Gait Pattern , 212-219. Publ. Scitepress, Valencia, Spain.	inproceedings
Abstract: This paper presents an approach for increasing the reactivity of a humanoid robot’s gait, incorporating Slow Feature Analysis (SFA), an unsupervised learning algorithm issuing from the domain of theoretical biology. The main objective of this work is to find a means to detect disturbances in the gait pattern at an early stage without losing stability. Another goal is to investigate the general potential of SFA for using it within sensorimotor loops which to our knowledge has not been considered until now. The application of SFA within sensorimotor loops is motivated by pointing out its relation to second-order Volterra filters. Our experiments show that the overall reactivity of the gait pattern increases without any profound loss in stability, and that SFA appears to be suitable for the usage even at such levels of sensorimotor control that are directly involved into motor activity regulation.
BibTeX: @inproceedings{HoeferHild-2010, author = {Sebastian H{\"{o}}fer and Manfred Hild}, title = {Using slow feature analysis to improve the reactivity of a humanoid robot's sensorimotor gait pattern}, booktitle = {Proceedings of the International Conference on Fuzzy Computation and 2\textsuperscript{nd} International Conference on Neural Computation}, publisher = {Scitepress}, year = {2010}, pages = {212--219}, url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0003082102120219}, url2 = {http://www.sebastianhoefer.de/publications/Hoefer_Hild-SFA_Sensorimotor_cr.pdf}, doi = {http://doi.org/10.5220/0003082102120219} }
Höfer, S.; Hild, M. & Kubisch, M.	2010	Using slow feature analysis to extract behavioural manifolds related to humanoid robot postures [Abstract] [BibTeX] [URL(2)]	Tenth International Conference on Epigenetic Robotics , Using Slow Feature Analysis to Extract Behavioural Manifolds Related to Humanoid Robot Postures , 43-50. , Örenas, Sweden	inproceedings
Abstract: This paper demonstrates how Slow Feature Analysis (SFA), an unsupervised learning algorithm stemming from the domain of theoretical biology, can be used to extract behavioural manifolds related to a humanoid robot's body postures. On one hand, we show that SFA detects abstract semantic features, encoding high-level behaviours, which can be used for representation making and the classiffication of the robot's posture; on the other hand we propose a method for analysing the obtained SFA components in terms of the manifold that contains the robot's sensory states belonging to the detected postures. This allows further characterisation of the SFA results as well as a possible means for directed exploration of the sensory state space.
BibTeX: @inproceedings{HoeferHildEtAl-2010, author = {Sebastian H{\"{o}}fer and Manfred Hild and Matthias Kubisch}, title = {Using slow feature analysis to extract behavioural manifolds related to humanoid robot postures}, booktitle = {Tenth International Conference on Epigenetic Robotics}, year = {2010}, pages = {43--50}, url2 = {http://www.sebastianhoefer.de/publications/Hoefer_et_al-SFA_Behavioural_Manifolds.pdf} }
Höfer, S.; Spranger, M. & Hild, M.	2012	Posture recognition based on slow feature analysis [Abstract] [BibTeX] [URL]	Language Grounding in Robots , 111-130. Eds. Steels, L. & Hild, M. Publ. Springer.	incollection
Abstract: Basic postures such as sit, stand and lie are ubiquitous in human interaction. In order to build robots that aid and support humans in their daily life, we need to understand how posture categories can be learned and recognized. This paper presents an unsupervised learning approach to posture recognition for a biped humanoid robot. The approach is based on Slow Feature Analysis (SFA), a biologically inspired algorithm for extracting slowly changing signals from signals varying on a fast time scale. Two experiments are carried out: First, we consider the problem of recognizing static postures in a multimodal sensory stream which consists of visual and proprioceptive stimuli. Secondly, we show how to extract a low-dimensional representation of the sensory state space which is suitable for posture recognition in a more complex setting. We point out that the beneficial performance of SFA in this task can be related to the fact that SFA computes manifolds which are used in robotics to model invariants in motion and behavior. Based on this insight, we also propose a method for using SFA components for guided exploration of the state space.
BibTeX: @incollection{HoeferSprangerEtAl-2012, author = {Sebastian H{\"{o}}fer and Michael Spranger and Manfred Hild}, title = {Posture recognition based on slow feature analysis}, booktitle = {Language Grounding in Robots}, publisher = {Springer}, year = {2012}, pages = {111--130}, url = {http://link.springer.com/chapter/10.1007/978-1-4614-3064-3_6}, doi = {http://doi.org/10.1007/978-1-4614-3064-3_6} }
Hong, H.; Jiang, C.; Peng, X. & Zhong, W.	2020	Concurrent Monitoring Strategy for Static and Dynamic Deviations Based on Selective Ensemble Learning Using Slow Feature Analysis [Abstract] [BibTeX] [URL]	Industrial & Engineering Chemistry Research , 59(10), 4620-4635.	article
Abstract: Slow feature analysis (SFA) has been extensively adopted for process monitoring. Since the prominent ability of exploring dynamic information of the industrial process, SFA could monitor the process static and dynamic deviations concurrently. However, for complex and large-scale processes, it is difficult for a single SFA model to monitor the whole process well because of the complex relationship within massive volumes of variables. To address this issue and get a better monitoring performance, a novel ensemble process monitoring method based on slow feature analysis models is proposed as ensemble SFA (ESFA) in this paper. The proposed method develops a set of SFA models based on different combinations of variables, and the divisive hierarchical clustering algorithm (DHCA) is performed to pick out some models with great diversity as the base learners. Then, the fault detection results of base models would be combined into a comprehensive indicator through Bayesian inference. Furthermore, the ESFA method also provides an ES2 statistic for monitoring process dynamics to differentiate the deviations of normal operating condition changes from dynamic anomalies incurred by real faults. Finally, compared with basic SFA and several principal component analysis (PCA)-based methods, the validity of the proposed method is demonstrated through the case studies of the Tennessee Eastman (TE) benchmark process and the BSM1 process.
BibTeX: @article{doi:10.1021/acs.iecr.9b05547, author = {Hong, Huifen and Jiang, Chao and Peng, Xin and Zhong, Weimin}, title = {Concurrent Monitoring Strategy for Static and Dynamic Deviations Based on Selective Ensemble Learning Using Slow Feature Analysis}, journal = {Industrial \& Engineering Chemistry Research}, year = {2020}, volume = {59}, number = {10}, pages = {4620-4635}, url = {https://doi.org/10.1021/acs.iecr.9b05547}, doi = {http://doi.org/10.1021/acs.iecr.9b05547} }
Hu, X.; Hu, S.; Huang, Y.; Zhang, H. & Wu, H.	2016	Video anomaly detection using deep incremental slow feature analysis network [BibTeX] [URL]	IET Computer Vision . Publ. IET.	article
BibTeX: @article{HuHuEtAl-2016, author = {Hu, Xing and Hu, Shiqiang and Huang, Yingping and Zhang, Huanlong and Wu, Hanbing}, title = {Video anomaly detection using deep incremental slow feature analysis network}, journal = {IET Computer Vision}, publisher = {IET}, year = {2016}, url = {https://mr.crossref.org/iPage?doi=10.1049/iet-cvi.2015.0271}, doi = {http://doi.org/10.1049/iet-cvi.2015.0271} }
Huang, J.; Ersoy, O.K. & Yan, X.	2017	Slow feature analysis based on online feature reordering and feature selection for dynamic chemical process monitoring [Abstract] [BibTeX] [URL(2)]	Chemometrics and Intelligent Laboratory Systems , 169, 1-11.	article
Abstract: This study considers the insufficiency of traditional monitoring methods to eliminate dynamics, and proposes a novel online feature reordering- and feature selection-based slow feature analysis (SFA) algorithm. The SFA algorithm explores the process dynamics from the view of inner variation of data to extract the slowly varying features. The extracted SFs are considered as the representations of steady- and dynamic-state processes. Online feature reordering and feature selection strategies maximize online fault information and can be used to perform fault detection operation. The proposed method is applied to two simulated processes. Monitoring results show that the proposed method has better monitoring results than those of traditional methods.
BibTeX: @article{HUANG20171, author = {Jian Huang and Okan K. Ersoy and Xuefeng Yan}, title = {Slow feature analysis based on online feature reordering and feature selection for dynamic chemical process monitoring}, journal = {Chemometrics and Intelligent Laboratory Systems}, year = {2017}, volume = {169}, pages = {1-11}, url2 = {https://www.sciencedirect.com/science/article/pii/S0169743917301375}, doi = {http://doi.org/10.1016/j.chemolab.2017.07.013} }
Huang, J.; Ersoy, O.K. & Yan, X.	2019	Fault detection in dynamic plant-wide process by multi-block slow feature analysis and support vector data description [Abstract] [BibTeX] [URL(2)]	ISA transactions , 85, 119-128. Publ. Elsevier.	article
Abstract: This study describes a dynamic large-scale process fault detection algorithm based on multi-block slow feature analysis by taking advantages of both multi-block algorithms in highlighting the local information and slow feature analysis in extracting the different dynamics of process data. A mutual information-based relevance matrix is first calculated to measure the correlation between any two variables, and then K-means clustering is used to cluster the original variables into several blocks by gathering the variables with similar relevance vectors into the same block. Slow feature analysis is applied in each block. A support vector data description is utilized to give a final decision. The proposed algorithm is tested with a well-known Tennessee Eastman (TE) process. The fault detection results show the efficiency and the superiority of the proposed method as compared to other related methods.
BibTeX: @article{huang2019fault, author = {Huang, Jian and Ersoy, Okan K and Yan, Xuefeng}, title = {Fault detection in dynamic plant-wide process by multi-block slow feature analysis and support vector data description}, journal = {ISA transactions}, publisher = {Elsevier}, year = {2019}, volume = {85}, pages = {119--128}, url2 = {https://www.researchgate.net/publication/328486141_Fault_detection_in_dynamic_plant-wide_process_by_multi-block_slow_feature_analysis_and_support_vector_data_description} }
Huang, J.; Yang, X.; Shardt, Y.A.W. & Yan, X.	2020	Fault Classification in Dynamic Processes Using Multiclass Relevance Vector Machine and Slow Feature Analysis [Abstract] [BibTeX] [URL]	IEEE Access , 8, 9115-9123.	article
Abstract: This paper proposes a modified relevance vector machine with slow feature analysis fault classification for industrial processes. Traditional support vector machine classification does not work well when there are insufficient training samples. A relevance vector machine, which is a Bayesian learning-based probabilistic sparse model, is developed to determine the probabilistic prediction and sparse solutions for the fault category. This approach has the benefits of good generalization ability and robustness to small training samples. To maximize the dynamic separability between classes and reduce the computational complexity, slow feature analysis is used to extract the inner dynamic features and reduce the dimension. Experiments comparing the proposed method, relevance vector machine and support vector machine classification are performed using the Tennessee Eastman process. For all faults, relevance vector machine has a classification rate of 39 while the proposed algorithm has an overall classification rate of 76.1%. This shows the efficiency and advantages of the proposed method.
BibTeX: @article{8941098, author = {Huang, Jian and Yang, Xu and Shardt, Yuri A. W. and Yan, Xuefeng}, title = {Fault Classification in Dynamic Processes Using Multiclass Relevance Vector Machine and Slow Feature Analysis}, journal = {IEEE Access}, year = {2020}, volume = {8}, pages = {9115-9123}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8941098}, doi = {http://doi.org/10.1109/ACCESS.2019.2962008} }
Huang, J.; Yang, X. & Yan, X.	2020	Slow feature analysis-independent component analysis based integrated monitoring approach for industrial processes incorporating dynamic and static characteristics [Abstract] [BibTeX] [URL]	Control Engineering Practice , 102, 104558.	article
Abstract: Considering dynamic and static characteristics in industrial processes, this paper proposed an integrated monitoring approach based on slow feature analysis and independent component analysis (SFA-ICA), which can fully take advantage of SFA and ICA in extracting dynamic features and static non-Gaussian features. A sequential correlation-based matrix for each variable is first calculated to evaluate the dynamics of the process variable, in which, the variables with weak autocorrelation and cross-correlation are considered as static variables, while the others are dynamic variables. Then, the ICA and SFA algorithms are built for the static and dynamic subspaces. The statistics from each of the subspaces are combined using Bayesian inference to give a final comprehensive statistic. The proposed SFA-ICA monitoring approach is applied to a numerical example, the Tennessee Eastman (TE) process and the continuous stirred tank reactor (CSTR) process. Results show that the SFA-ICA achieves the better fault detection rates for the numerical example, the CSTR process, and several typical faults for TE process.
BibTeX: @article{HUANG2020104558, author = {Jian Huang and Xu Yang and Xuefeng Yan}, title = {Slow feature analysis-independent component analysis based integrated monitoring approach for industrial processes incorporating dynamic and static characteristics}, journal = {Control Engineering Practice}, year = {2020}, volume = {102}, pages = {104558}, url = {https://www.sciencedirect.com/science/article/pii/S0967066120301532}, doi = {http://doi.org/10.1016/j.conengprac.2020.104558} }
Huang, X.; Zhu, T.; Zhang, L. & Tang, Y.	2014	A novel building change index for automatic building change detection from high-resolution remote sensing imagery [Abstract] [BibTeX] [URL] [URL(2)]	Remote Sensing Letters , 5(8), 713-722. Publ. Taylor & Francis.	article
Abstract: In pace with rapid urbanization, urban areas in many countries are undergoing huge changes. The large spectral variance and spatial heterogeneity within the ‘buildings’ land cover class, as well as the similar spectral properties between buildings and other urban structures, make building change detection a challenging problem. In this work, we propose a set of novel building change indices (BCIs) by combining morphological building index (MBI) and slow feature analysis (SFA) for building change detection from high-resolution imagery. MBI is a recently developed automatic building detector for high-resolution imagery, which is able to highlight building components but simultaneously suppress other urban structures. SFA is an unsupervised learning algorithm that can discriminate the changed components from the unchanged ones for multitemporal images. By effectively integrating the information from MBI and SFA, the building change components can be automatically generated. Experiments conducted on the QuickBird 2002–2005 data-set are used to validate the effectiveness of the proposed building change detection framework.
BibTeX: @article{HuangZhuEtAl-2014, author = {Huang, Xin and Zhu, Tingting and Zhang, Liangpei and Tang, Yuqi}, title = {A novel building change index for automatic building change detection from high-resolution remote sensing imagery}, journal = {Remote Sensing Letters}, publisher = {Taylor \& Francis}, year = {2014}, volume = {5}, number = {8}, pages = {713--722}, url = {http://www.tandfonline.com/doi/abs/10.1080/2150704X.2014.963732}, url2 = {http://www.lmars.whu.edu.cn/prof_web/zhangliangpei/rs/publication/A%20novel%20building%20change%20index%20for%20automatic%20building%20change%20detection%20from%20high-resolution%20remote%20sensing%20imagery.pdf}, doi = {http://doi.org/10.1080/2150704x.2014.963732} }
Huang, Y.; Zhao, J.; Liu, Y.; Luo, S.; Zou, Q. & Tian, M.	2011	Nonlinear dimensionality reduction using a temporal coherence principle [Abstract] [BibTeX] [URL]	Information Sciences , 181(16), 3284-3307. Publ. Elsevier BV.	article
Abstract: Temporal coherence principle is an attractive biologically inspired learning rule to extract slowly varying features from quickly varying input data. In this paper we develop a new Nonlinear Neighborhood Preserving (NNP) technique, by utilizing the temporal coherence principle to find an optimal low dimensional representation from the original high dimensional data. NNP\ is based on a nonlinear expansion of the original input data, such as polynomials of a given degree. It can be solved by the eigenvalue problem without using gradient descent and is guaranteed to find the global optimum. NNP\ can be viewed as a nonlinear dimensionality reduction framework which takes into consideration both time series and data sets without an obvious temporal structure. According to different situations, we introduce three algorithms of NNP, named NNP-1, NNP-2, and NNP-3. The objective function of NNP-1 is equal to Slow Feature Analysis (SFA), and it works well for time series such as image sequences. NNP-2 artificially constructs time series consisting of neighboring points for data sets without a clear temporal structure such as image data. NNP-3 is proposed for classification tasks, which can minimize the distances of neighboring points in the embedding space and ensure that the remaining points are as far apart as possible simultaneously. Furthermore, the kernel extension of NNP\ is also discussed in this paper. The proposed algorithms work very well on some image sequences and image data sets compared to other methods. Meanwhile, we perform the classification task on the MNIST\ handwritten digit database using the supervised NNP\ algorithms. The experimental results demonstrate that NNP\ is an effective technique for nonlinear dimensionality reduction tasks.
BibTeX: @article{HuangZhaoEtAl-2011, author = {YaPing Huang and JiaLi Zhao and YunHui Liu and SiWei Luo and Qi Zou and Mei Tian}, title = {Nonlinear dimensionality reduction using a temporal coherence principle}, journal = {Information Sciences}, publisher = {Elsevier {BV}}, year = {2011}, volume = {181}, number = {16}, pages = {3284--3307}, url = {http://www.sciencedirect.com/science/article/pii/S0020025511001691}, doi = {http://doi.org/10.1016/j.ins.2011.04.001} }
Huang, Y.; Zhao, J.; Tian, M.; Zou, Q. & Luo, S.	2009	Slow feature discriminant analysis and its application on handwritten digit recognition [Abstract] [BibTeX] [URL]	Conference on Neural Networks, 2009. IJCNN 2009. International Joint , 1294-1297.	inproceedings
Abstract: Slow feature analysis (SFA) is an unsupervised algorithm by extracting the slowly varying features from time series and has been used to pattern recognition successfully. Based on SFA, this paper develops a new algorithm, Slow feature discriminant analysis (SFDA), which can maximize the temporal variation of between-class time series, and minimize the temporal variation of within-class time series simultaneously. Due to adoption of discrimination power, the performance on pattern recognition is improved compared to SFA. The experiments results on MNIST digit handwritten database also show that the proposed algorithm is in particular attractive.
BibTeX: @inproceedings{HuangZhaoEtAl-2009, author = {Yaping Huang and Jiali Zhao and Mei Tian and Qi Zou and Siwei Luo}, title = {Slow feature discriminant analysis and its application on handwritten digit recognition}, booktitle = {Conference on Neural Networks, 2009. IJCNN 2009. International Joint}, year = {2009}, pages = {1294--1297}, url = {http://ieeexplore.ieee.org/document/5178596/}, doi = {http://doi.org/10.1109/IJCNN.2009.5178596} }
Hyvärinen, A.; Hurri, J. & Hoyer, P.O.	2009	Natural image statistics: a probabilistic approach to early computational vision. [Abstract] [BibTeX] [URL(2)]	, 39. Publ. Springer Science & Business Media.	book
Abstract: This book is both an introductory textbook and a research monograph on modelling the statistical structure of natural images. In very simple terms, “natural images” are photographs of the typical environment where we live. In this book, their statistical structure is described using a number of statistical models whose parameters are estimated from image samples. Our main motivation for exploring natural image statistics is computational mod- elling of biological visual systems. A theoretical framework which is gaining more and more support considers the properties of the visual system to be reflections of the statistical structure of natural images, because of evolutionary adaptation pro- cesses. Another motivation for natural image statistics research is in computer sci- ence and engineering, where it helps in development of better image processing and computer vision methods. While research on natural image statistics has been growingrapidly since the mid-1990’s, no attempt has been made to cover the field in a single book, providing a unified view of the different models and approaches. This book attempts to do just that. Furthermore, our aim is to provide an accessible introduction to the field for students in related disciplines. However, not all aspects of such a large field of study can be completely covered in a single book, so we have had to make some choices. Basically, we concentrate on the neural modelling approaches at the expense of engineering applications. Fur- thermore, those topics on which the authors themselves havebeen doing research are, inevitably, given more emphasis
BibTeX: @book{HyvaerinenHurriEtAl-2009, author = {Hyv{\"a}rinen, Aapo and Hurri, Jarmo and Hoyer, Patrick O}, title = {Natural image statistics: a probabilistic approach to early computational vision.}, publisher = {Springer Science \& Business Media}, year = {2009}, volume = {39}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.207.5015&rep=rep1&type=pdf} }
Ilin, A.; Valpola, H. & Oja, E.	2006	Exploratory analysis of climate data using source separation methods [Abstract] [BibTeX] [URL] [URL(2)]	Neural Networks , 19(2), 155-167. Publ. Elsevier.	article
Abstract: We present an example of exploratory data analysis of climate measurements using a recently developed denoising source separation (DSS) framework. We analyzed a combined dataset containing daily measurements of three variables: surface temperature, sea level pressure and precipitation around the globe, for a period of 56 years. Components exhibiting slow temporal behavior were extracted using DSS with linear denoising. The first component, most prominent in the interannual time scale, captured the well-known El Nino-Southern Oscillation (ENSO) phenomenon and the second component was close to the derivative of the first one. The slow components extracted in a wider frequency range were further rotated using a frequency-based separation criterion implemented by DSS with nonlinear denoising. The rotated sources give a meaningful representation of the slow climate variability as a combination of trends, interannual oscillations, the annual cycle and slowly changing seasonal variations. Again, components related to the ENSO phenomenon emerge very clearly among the found sources.
BibTeX: @article{IlinValpolaEtAl-2006, author = {Ilin, Alexander and Valpola, Harri and Oja, Erkki}, title = {Exploratory analysis of climate data using source separation methods}, journal = {Neural Networks}, publisher = {Elsevier}, year = {2006}, volume = {19}, number = {2}, pages = {155--167}, url = {http://www.sciencedirect.com/science/article/pii/S0893608006000086}, url2 = {https://pdfs.semanticscholar.org/6547/94fc04980944f3cdad6097d9ccde203bded0.pdf}, doi = {http://doi.org/10.1016/j.neunet.2006.01.011} }
Jayaraman, D. & Grauman, K.	2015	Slow and steady feature analysis: higher order temporal coherence in video [Abstract] [BibTeX] [URL]	e-print arXiv:1506.04714 .	misc
Abstract: How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture how the visual content changes. We propose to generalize slow feature analysis to "steady" feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.
BibTeX: @misc{JayaramanGrauman-2015, author = {Jayaraman, Dinesh and Grauman, Kristen}, title = {Slow and steady feature analysis: higher order temporal coherence in video}, year = {2015}, howpublished = {e-print arXiv:1506.04714}, url = {https://arxiv.org/abs/1506.04714} }
Jayaraman, D. & Grauman, K.	2016	Slow and steady feature analysis: higher order temporal coherence in video [Abstract] [BibTeX] [URL]	2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 3852-3861.	inproceedings
Abstract: How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture how the visual content changes. We propose to generalize slow feature analysis to "steady" feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.
BibTeX: @inproceedings{JayaramanGrauman-2016, author = {D. Jayaraman and K. Grauman}, title = {Slow and steady feature analysis: higher order temporal coherence in video}, booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2016}, pages = {3852--3861}, url = {http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Jayaraman_Slow_and_Steady_CVPR_2016_paper.pdf}, doi = {http://doi.org/10.1109/CVPR.2016.418} }
Jia, P. & Chen, G.	2020	Wind Power Icing Fault Diagnosis Based on Slow Feature Analysis and Support Vector Machines [Abstract] [BibTeX] [URL]	2020 10th International Conference on Power and Energy Systems (ICPES) , 398-403.	inproceedings
Abstract: Blade icing is a worldwide problem in the field of wind power. A lot of prior knowledge is needed to detect blade icing by using mechanism modeling method, which cannot be satisfied in most cases. With the development of artificial intelligence (AI) technology, data-driven approaches have attracted widespread attention. In this paper, a combined strategy of slow feature analysis (SFA) and support vector machine (SVM) is proposed to detect the icing fault of wind blades. It is significant to improve the reliability and economy of wind turbines. First, SFA is used to extract the features that change slowly in the process. After that, the extracted slow features are input into SVM for fault detection. The lowest error rate of the proposed method is 0.234 when the number of show features is reduced to 5 while it is 0.317 by directly putting into SVM, which is verified by wind power experiments. So it is crucial to select the number of slow features.
BibTeX: @inproceedings{9349697, author = {Jia, Peng and Chen, Guangyu}, title = {Wind Power Icing Fault Diagnosis Based on Slow Feature Analysis and Support Vector Machines}, booktitle = {2020 10th International Conference on Power and Energy Systems (ICPES)}, year = {2020}, pages = {398-403}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9349697}, doi = {http://doi.org/10.1109/ICPES51309.2020.9349697} }
Jiang, C.; Zhong, W.; Li, Z.; Peng, X. & Yang, M.	2019	Real-Time Semisupervised Predictive Modeling Strategy for Industrial Continuous Catalytic Reforming Process with Incomplete Data Using Slow Feature Analysis [Abstract] [BibTeX] [URL]	Industrial & Engineering Chemistry Research , 58(37), 17406-17423.	article
Abstract: The catalytic naphtha reforming process is one of the most significant processes in the petrochemical industry. This process is notable for its function of transforming petroleum refinery naphtha from crude oil with low octane ratings into high-octane premium blending stocks, namely, gasoline or aromatic hydrocarbons. This process consists of many units along with complicated chemical reactions, which leads to large-scale and strong coupling, with time variation and nonlinearity to some extent. Under such circumstances, it remains a great challenge to control and optimize the catalytic reforming process. To evaluate the current operational status of the catalytic reforming process, there is a need for online assessment of some key quality-related indices for engineers as a reference. Among these indices, research octane number (RON) barrel is widely used for the evaluation of gasoline quality. However, traditional measurement methods are often time-consuming, labor-consuming, and expensive. To overcome such drawbacks, a data-driven predictive model for the prediction of RON barrel values is proposed in this study. Considering data from real industry are often contaminated with noise and other uncertain factors, conventional data-driven prediction methods may fail in the extraction of useful process information. Meanwhile, missing data is also commonly observed in real industrial samples. To deal with these problems, the proposed predictive model employs a semisupervised learning-based just-in-time learning framework. Different from traditional just-in-time learning frameworks, variable selection is taken into consideration in the proposed framework, in addition to sample selection. And both selection approaches proceed on the basis of the symmetric Kullback–Leibler divergence, which measures the distributional dissimilarities among samples or variables, to reduce the noise influence. Additionally, variational Bayesian principal component analysis, which is known as an effective generative model, is exploited to alleviate the missing data problem. Eventually, a novel nonlinear slow feature analysis algorithm, namely, locally weighted slow feature analysis, is put forward to model the time variance and nonlinearity of this process. To better validate the efficiency and superiority of the proposed method, an industrial case study is conducted with data collected from a real industrial catalytic reforming process, where missing data percentage ranges from 0.1 to 10%. The qualitative and quantitative results demonstrate that the proposed technique can outperform some conventional data-driven methods.
BibTeX: @article{doi:10.1021/acs.iecr.9b03119, author = {Jiang, Chao and Zhong, Weimin and Li, Zhi and Peng, Xin and Yang, Minglei}, title = {Real-Time Semisupervised Predictive Modeling Strategy for Industrial Continuous Catalytic Reforming Process with Incomplete Data Using Slow Feature Analysis}, journal = {Industrial \& Engineering Chemistry Research}, year = {2019}, volume = {58}, number = {37}, pages = {17406-17423}, url = { https://doi.org/10.1021/acs.iecr.9b03119}, doi = {http://doi.org/10.1021/acs.iecr.9b03119} }
Jonschkowski, R. & Brock, O.	2013	Learning task-specific state representations by maximizing slowness and predictability [Abstract] [BibTeX] [URL(2)]	6^th international workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems (ERLARS) .	inproceedings
Abstract: The success of reinforcement learning in robotic tasks is highly dependent on the state representation – a mapping from high dimensional sensory observations of the robot to states that can be used for reinforcement learning. Even though many methods have been proposed to learn state representations, it remains an important open problem. Identifying the characteristics existing methods are optimizing to find good state representations, combining them, and adding new characteristics will lead to a more robust method for state representation learning. We define a new characteristic – predictabil- ity – and combine it with slowness. We implement these character- istics in a neural network and show that this approach can find good state representations from visual input in simulated robotic tasks.
BibTeX: @inproceedings{JonschkowskiBrock-2013, author = {Jonschkowski, Rico and Brock, Oliver}, title = {Learning task-specific state representations by maximizing slowness and predictability}, booktitle = {6\textsuperscript{th} international workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems (ERLARS)}, year = {2013}, url2 = {https://pdfs.semanticscholar.org/6b9c/9aafca671898f0ec29e1c7a9d1799a51d41b.pdf} }
Jonschkowski, R. & Brock, O.	2014	State representation learning in robotics: using prior knowledge about physical interaction [Abstract] [BibTeX] [URL]	Robotics: Science and Systems (RSS) .	inproceedings
Abstract: State representations critically affect the effective- ness of learning in robots. In this paper, we propose a robotics- specific approach to learning such state representations. Robots accomplish tasks by interacting with the physical world. Physics in turn imposes structure on both the changes in the world and on the way robots can effect these changes. Using prior knowledge about interacting with the physical world, robots can learn state representations that are consistent with physics. We identify five robotic priors and explain how they can be used for representation learning. We demonstrate the effectiveness of this approach in a simulated slot car racing task and a simulated navigation task with distracting moving objects. We show that our method extracts task-relevant state representations from high- dimensional observations, even in the presence of task-irrelevant distractions. We also show that the state representations learned by our method greatly improve generalization in reinforcement learning.
BibTeX: @inproceedings{JonschkowskiBrock-2014, author = {Jonschkowski, Rico and Brock, Oliver}, title = {State representation learning in robotics: using prior knowledge about physical interaction}, booktitle = {Robotics: Science and Systems (RSS)}, year = {2014}, url = {http://www.roboticsproceedings.org/rss10/p19.pdf}, doi = {http://doi.org/10.15607/rss.2014.x.019} }
Jonschkowski, R.; Höfer, S. & Brock, O.	2015	Patterns for learning with side information [Abstract] [BibTeX] [URL]	e-print arXiv:1511.06429 .	misc
Abstract: Supervised, semi-supervised, and unsupervised learning estimate a function given input/output samples. Generalization of the learned function to unseen data can be improved by incorporating side information into learning. Side information are data that are neither from the input space nor from the output space of the function, but include useful information for learning it. In this paper we show that learning with side information subsumes a variety of related approaches, e.g. multi-task learning, multi-view learning and learning using privileged information. Our main contributions are (i) a new perspective that connects these previously isolated approaches, (ii) insights about how these methods incorporate different types of prior knowledge, and hence implement different patterns, (iii) facilitating the application of these methods in novel tasks, as well as (iv) a systematic experimental evaluation of these patterns in two supervised learning tasks.
BibTeX: @misc{JonschkowskiHoeferEtAl-2015, author = {{Jonschkowski}, R. and {H{\"o}fer}, S. and {Brock}, O.}, title = {Patterns for learning with side information}, year = {2015}, howpublished = {e-print arXiv:1511.06429}, url = {https://arxiv.org/abs/1511.06429} }
Kamal, S.; Supriya, M.H. & Pillai, P.R.S.	2011	Blind source separation of nonlinearly mixed ocean acoustic signals using slow feature analysis [Abstract] [BibTeX] [URL]	OCEANS 2011 IEEE - Spain , 1-7. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: The ocean acoustic environment is astoundingly complex, consisting of numerous noise sources like ships, offshore oil rigs, marine life, shore waves and acoustic cavitations, featuring varying sound speed profiles, multi-path interferences, as well as other hydrodynamic phenomena. Irrespective of the type of the receiver system, whether active or passive, the signals picked up by the hydrophones are disturbed by these inherent anomalies of the propagating medium and poses a prime challenge to extract useful information from the chaotic mixtures of received signals. Blind Source Separation (BSS), an engineering paradigm which attempts to mimic the human cognitive capability of selectively extracting an interesting process amidst several similar competing processes, can be considered as a viable solution to the problem. In this paper, the effectiveness of Slow Feature Analysis (SFA) algorithm (Laurenz Wiskott et.al), a biologically motivated technique based on the concept of temporal slowness to extract invariant features from multivariate time series, for solving the problem of nonlinear BSS is investigated. A testing framework for underwater acoustic signal separation has been developed in Python with the aid of Modular toolkit for Data Processing (MDP), a stack of general purpose machine learning algorithms.
BibTeX: @inproceedings{KamalSupriyaEtAl-2011, author = {Suraj Kamal and M. H. Supriya and P. R. Saseendran Pillai}, title = {Blind source separation of nonlinearly mixed ocean acoustic signals using slow feature analysis}, booktitle = {{OCEANS} 2011 {IEEE} - Spain}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {1--7}, url = {http://ieeexplore.ieee.org/document/6003620/}, doi = {http://doi.org/10.1109/oceans-spain.2011.6003620} }
Karhunen, J.; Hao, T. & Ylipaavalniemi, J.	2012	A canonical correlation analysis based method for improving BSS of two related data sets [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Latent Variable Analysis and Signal Separation , 91-98. Publ. Springer Nature.	inproceedings
Abstract: We consider an extension of ICA and BSS for separating mutually dependent and independent components from two related data sets. We propose a new method which first uses canonical correlation analysis for detecting subspaces of independent and dependent components. Different ICA and BSS methods can after this be used for final separation of these components. Our method has a sound theoretical basis, and it is straightforward to implement and computationally not demanding. Experimental results on synthetic and real-world fMRI data sets demonstrate its good performance.
BibTeX: @inproceedings{KarhunenHaoEtAl-2012, author = {Karhunen, Juha and Hao, Tele and Ylipaavalniemi, Jarkko}, title = {A canonical correlation analysis based method for improving {BSS} of two related data sets}, booktitle = {International Conference on Latent Variable Analysis and Signal Separation}, publisher = {Springer Nature}, year = {2012}, pages = {91--98}, url = {http://link.springer.com/chapter/10.1007/978-3-642-28551-6_12}, url2 = {https://pdfs.semanticscholar.org/f7e4/65da1276d9c7bd5d3b8b844947119692f453.pdf}, doi = {http://doi.org/10.1007/978-3-642-28551-6_12} }
Karhunen, J.; Hao, T. & Ylipaavalniemi, J.	2012	A generalized canonical correlation analysis based method for blind source separation from related data sets [Abstract] [BibTeX] [URL] [URL(2)]	The 2012 International Joint Conference on Neural Networks (IJCNN) , 1-9. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: In this paper, we consider an extension of independent component analysis (ICA) and blind source separation (BSS) techniques to several related data sets. The goal is to separate mutually dependent and independent components or source signals from these data sets. This problem is important in practice, because such data sets are common in real-world applications. We propose a new method which first uses a generalization of standard canonical correlation analysis (CCA) for detecting subspaces of independent and dependent components. Any ICA or BSS method can after this be used for final separation of these components. The proposed method performs well for synthetic data sets for which the assumed data model holds, and provides interesting and meaningful results for real-world functional magnetic resonance imaging (fMRI) data. The method is straightforward to implement and computationally not too demanding. The proposed method improves clearly the separation results of several well-known ICA and BSS methods compared with the situation in which generalized CCA is not used.
BibTeX: @inproceedings{KarhunenHaoEtAl-2012a, author = {Karhunen, Juha and Hao, Tele and Ylipaavalniemi, Jarkko}, title = {A generalized canonical correlation analysis based method for blind source separation from related data sets}, booktitle = {The 2012 International Joint Conference on Neural Networks ({IJCNN})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2012}, pages = {1--9}, url = {http://ieeexplore.ieee.org/document/6252708/}, url2 = {https://pdfs.semanticscholar.org/d82b/f16c2ad8e4663fae13e964144bc9ac745de4.pdf}, doi = {http://doi.org/10.1109/ijcnn.2012.6252708} }
Karhunen, J.; Hao, T. & Ylipaavalniemi, J.	2013	Finding dependent and independent components from related data sets: a generalized canonical correlation analysis based method [BibTeX] [URL(2)]	Neurocomputing , 113, 153-167. Publ. Elsevier.	article
BibTeX: @article{KarhunenHaoEtAl-2013, author = {Karhunen, Juha and Hao, Tele and Ylipaavalniemi, Jarkko}, title = {Finding dependent and independent components from related data sets: a generalized canonical correlation analysis based method}, journal = {Neurocomputing}, publisher = {Elsevier}, year = {2013}, volume = {113}, pages = {153--167}, url2 = {http://research.ics.aalto.fi/publications/bibdb2012/public_pdfs/Final_NEUCOM_Aug2013.pdf} }
Kerenidis, I. & Luongo, A.	2020	Classification of the MNIST data set with quantum slow feature analysis [Abstract] [BibTeX] [URL]	Physical Review A , 101(6). Publ. American Physical Society (APS).	article
Abstract: Quantum machine learning is a research discipline intersecting quantum algorithms and machine learning. While a number of quantum algorithms with potential speedups have been proposed, it is quite difficult to provide evidence that quantum computers will be useful to solve real-world problems. Our work makes progress towards this goal. In this work, we design quantum algorithms for dimensionality reduction and for classification, and combine them to provide a quantum classifier that we test on the MNIST dataset of handwritten digits. We simulate the quantum classifier, including errors in the quantum procedures, and show that it can provide classification accuracy of 98.5%. The running time of the quantum classifier is only polylogarithmic in the dimension and number of data points. Furthermore, we provide evidence that the other parameters on which the running time depends scale favorably, ascertaining the efficiency of our algorithm.
BibTeX: @article{2020, author = {Kerenidis, Iordanis and Luongo, Alessandro}, title = {Classification of the MNIST data set with quantum slow feature analysis}, journal = {Physical Review A}, publisher = {American Physical Society (APS)}, year = {2020}, volume = {101}, number = {6}, url = {http://dx.doi.org/10.1103/PhysRevA.101.062327}, doi = {http://doi.org/10.1103/physreva.101.062327} }
Kim, J.; Jeong, S.; Yu, Z. & Lee, M.	2013	Multiple timescale recurrent neural network with slow feature analysis for efficient motion recognition [Abstract] [BibTeX] [URL]	Neural Information Processing , Lecture Notes in Computer Science , 8227, 323-330. Eds. Lee, M.; Hirose, A.; Hou, Z.-G. & Kil, R. Publ. Springer Berlin Heidelberg.	incollection
Abstract: Multiple Timescale Recurrent Neural Network (MTRNN) model is a useful tool to learn and regenerate various kinds of action. In this paper, we use MTRNN as a dynamic model to analyze different human motions. Prediction error from dynamic model is used to classify different human actions. However, it is difficult to fully cover the human actions depending on the speed using dynamic model. In order to overcome the limitation of dynamic model, we considered Slow Feature analysis (SFA) which is used to extract the unique slow features from human actions data. In order to make input training data, we obtain 3 kinds of human actions by using KINECT. 3 dimensional slow feature data is be extracted by using SFA and those SFA feature data are used as the input of MTRNN for classification. The experiment results show that our proposed model performs better than the traditional model.
BibTeX: @incollection{KimJeongEtAl-2013, author = {Kim, Jihun and Jeong, Sungmoon and Yu, Zhibin and Lee, Minho}, title = {Multiple timescale recurrent neural network with slow feature analysis for efficient motion recognition}, booktitle = {Neural Information Processing}, publisher = {Springer Berlin Heidelberg}, year = {2013}, volume = {8227}, pages = {323--330}, url = {http://link.springer.com/chapter/10.1007/978-3-642-42042-9_41}, doi = {http://doi.org/10.1007/978-3-642-42042-9_41} }
Klampfl, S.	2007	Training of readouts with SFA [BibTeX]	.	article
BibTeX: @article{Klampfl-2007, author = {Klampfl, Stefan}, title = {Training of readouts with {SFA}}, year = {2007} }
Klampfl, S. & Maass, W.	2009	Replacing supervised classification learning by slow feature analysis in spiking neural networks [Abstract] [BibTeX] [URL(2)]	Proc. of NIPS 2009: Advances in Neural Information Processing Systems , 22, 988-996. Publ. MIT Press.	inproceedings
Abstract: Many models for computations in recurrent networks of neurons assume that the network state moves from some initial state to some fixed point attractor or limit cycle that represents the output of the computation. However experimental data show that in response to a sensory stimulus the network state moves from its initial state through a trajectory of network states and eventually returns to the initial state, without reaching an attractor or limit cycle in between. This type of network response, where salient information about external stimuli is encoded in characteristic trajectories of continuously varying network states, raises the question how a neural system could compute with such code, and arrive for example at a temporally stable classification of the external stimulus. We show that a known unsupervised learning algorithm, Slow Feature Analysis (SFA), could be an important ingredient for extracting stable information from these network trajectories. In fact, if sensory stimuli are more often followed by another stimulus from the same class than by a stimulus from another class, SFA approaches the classification capability of Fisher’s Linear Discriminant (FLD), a powerful algorithm for supervised learning. We apply this principle to simulated cortical microcircuits, and show that it enables readout neurons to learn discrimination of spoken digits and detection of repeating firing patterns within a stream of spike trains with the same firing statistics, without requiring any supervision for learning.
BibTeX: @inproceedings{KlampflMaass-2009, author = {S. Klampfl and W. Maass}, title = {Replacing supervised classification learning by slow feature analysis in spiking neural networks}, booktitle = {Proc. of NIPS 2009: Advances in Neural Information Processing Systems}, publisher = {MIT Press}, year = {2009}, volume = {22}, pages = {988--996}, url2 = {http://www.igi.tugraz.at/psfiles/192.pdf} }
Klampfl, S. & Maass, W.	2010	A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 22(12), 2979-3035. Publ. MIT Press - Journals.	article
Abstract: Neurons in the brain are able to detect and discriminate salient spatiotemporal patterns in the firing activity of presynaptic neurons. It is open how they can learn to achieve this, especially without the help of a supervisor. We show that a well-known unsupervised learning algorithm for linear neurons, slow feature analysis (SFA), is able to acquire the discrimination capability of one of the best algorithms for supervised linear discrimination learning, the Fisher linear discriminant (FLD), given suitable input statistics. We demonstrate the power of this principle by showing that it enables readout neurons from simulated cortical microcircuits to learn without any supervision to discriminate between spoken digits and to detect repeated firing patterns that are embedded into a stream of noise spike trains with the same firing statistics. Both these computer simulations and our theoretical analysis show that slow feature extraction enables neurons to extract and collect information that is spread out over a trajectory of firing states that lasts several hundred ms. In addition, it enables neurons to learn without supervision to keep track of time (relative to a stimulus onset, or the initiation of a motor response). Hence, these results elucidate how the brain could compute with trajectories of firing states rather than only with fixed point attractors. It also provides a theoretical basis for understanding recent experimental results on the emergence of view- and position-invariant classification of visual objects in inferior temporal cortex.
BibTeX: @article{KlampflMaass-2010, author = {Stefan Klampfl and Wolfgang Maass}, title = {A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2010}, volume = {22}, number = {12}, pages = {2979--3035}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00050}, url2 = {http://ai2-s2-pdfs.s3.amazonaws.com/7825/c75661c597ff6846153ab2f3aa330903512a.pdf}, doi = {http://doi.org/10.1162/NECO_a_00050} }
Koch, P.	2013	Efficient tuning in supervised machine learning [Abstract] [BibTeX] [URL] [URL(2)]	Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University, Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University .	phdthesis
Abstract: The tuning of learning algorithm parameters has become more and more important during the last years. With the fast growth of computational power and available memory databases have grown dramatically. This is very challenging for the tuning of parameters arising in machine learning, since the training can become very time-consuming for large datasets. For this reason efficient tuning methods are required, which are able to improve the predictions of the learning algorithms. In this thesis we incorporate model-assisted optimization techniques, for performing efficient optimization on noisy datasets with very limited budgets. Under this umbrella we also combine learning algorithms with methods for feature construction and selection. We propose to integrate a variety of elements into the learning process. E.g., can tuning be helpful in learning tasks like time series regression using state-of-the-art machine learning algorithms? Are statistical methods capable to reduce noise e ffects? Can surrogate models like Kriging learn a reasonable mapping of the parameter landscape to the quality measures, or are they deteriorated by disturbing factors? Summarizing all these parts, we analyze if superior learning algorithms can be created, with a special focus on efficient runtimes. Besides the advantages of systematic tuning approaches, we also highlight possible obstacles and issues of tuning. Di fferent tuning methods are compared and the impact of their features are exposed. It is a goal of this work to give users insights into applying state-of-the-art learning algorithms profitably in practice
BibTeX: @phdthesis{Koch-2013, author = {Koch, Patrick}, title = {Efficient tuning in supervised machine learning}, school = {Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University}, year = {2013}, url = {https://openaccess.leidenuniv.nl/handle/1887/22055}, url2 = {http://delta.cs.cinvestav.mx/~ccoello/EMOO/thesis-koch.pdf.gz} }
Koch, P.; Konen, W. & Hein, K.	2010	Gesture recognition on few training data using slow feature analysis and parametric bootstrap [Abstract] [BibTeX] [URL] [URL(2)]	The 2010 International Joint Conference on Neural Networks (IJCNN) , 1-8. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Slow Feature Analysis (SFA) has been established as a robust and versatile technique from the neurosciences to learn slowly varying functions from quickly changing signals. Recently, the method has been also applied to classification tasks. Here we apply SFA for the first time to a time series classification problem originating from gesture recognition. The gestures used in our experiments are based on acceleration signals of the Bluetooth Wiimote controller (Nintendo). We show that SFA achieves results comparable to the well-known Random Forest predictor in shorter computation time, given a sufficient number of training patterns. However - and this is a novelty to SFA classification - we discovered that SFA requires the number of training patterns to be strictly greater than the dimension of the nonlinear function space. If too few patterns are available, we find that the model constructed by SFA severely overfits and leads to high test set errors. We analyze the reasons for overfitting and present a new solution based on parametric bootstrap to overcome this problem.
BibTeX: @inproceedings{KochKonenEtAl-2010, author = {Patrick Koch and Wolfgang Konen and Kristine Hein}, title = {Gesture recognition on few training data using slow feature analysis and parametric bootstrap}, booktitle = {The 2010 International Joint Conference on Neural Networks ({IJCNN})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2010}, pages = {1--8}, url = {http://ieeexplore.ieee.org/document/5596842/}, url2 = {https://pdfs.semanticscholar.org/333e/c30ee5d3c6735bc35512f59d1ec5c9d93e48.pdf}, doi = {http://doi.org/10.1109/IJCNN.2010.5596842} }
Kompella, V.R.	2014	Slowness learning for curiosity-driven agents [Abstract] [BibTeX] [URL]	Università della Svizzera italiana, Università della Svizzera italiana .	phdthesis
Abstract: In the absence of external guidance, how can a robot learn to map the many raw pixels of high-dimensional visual inputs to useful action sequences? I study methods that achieve this by making robots self-motivated (curious) to continually build com- pact representations of sensory inputs that encode different aspects of the changing environment. Previous curiosity-based agents acquired skills by associating intrin- sic rewards with world model improvements, and used reinforcement learning (RL) to learn how to get these intrinsic rewards. But unlike in previous implementations, I consider streams of high-dimensional visual inputs, where the world model is a set of compact low-dimensional representations of the high-dimensional inputs. To learn these representations, I use the slowness learning principle, which states that the underlying causes of the changing sensory inputs vary on a much slower time scale than the observed sensory inputs. The representations learned through the slowness learning principle are called slow features (SFs). Slow features have been shown to be useful for RL, since they capture the underlying transition process by extracting spatio-temporal regularities in the raw sensory inputs. However, existing techniques that learn slow features are not readily applicable to curiosity-driven on- line learning agents, as they estimate computationally expensive covariance matrices from the data via batch processing. The first contribution called the incremental SFA (IncSFA), is a low-complexity, online algorithm that extracts slow features without storing any input data or esti- mating costly covariance matrices, thereby making it suitable to be used for several online learning applications. However, IncSFA gradually forgets previously learned representations whenever the statistics of the input change. In open-ended online learning, it becomes essential to store learned representations to avoid re-learning previously learned inputs. The second contribution is an online active modular IncSFA algorithm called the curiosity-driven modular incremental slow feature analysis (Curious Dr. MISFA). Curious Dr. MISFA addresses the forgetting problem faced by IncSFA and learns expert slow feature abstractions in order from least to most costly, with theoretical guarantees. The third contribution uses the Curious Dr. MISFA algorithm in a continual curiosity-driven skill acquisition framework that enables robots to acquire, store, and re-use both abstractions and skills in an online and continual manner. I provide (a) a formal analysis of the working of the proposed algorithms; (b) compare them to the existing methods; and (c) use the iCub humanoid robot to demonstrate their application in real-world environments. These contributions to- gether demonstrate that the online implementations of slowness learning make it suitable for an open-ended curiosity-driven RL agent to acquire a repertoire of skills that map the many raw pixels of high-dimensional images to multiple sets of action sequences.
BibTeX: @phdthesis{Kompella-2014, author = {Kompella, Varun Raj}, title = {Slowness learning for curiosity-driven agents}, school = {Universit{\`a} della Svizzera italiana}, year = {2014}, url = {http://doc.rero.ch/record/234698/files/2014INFO013.pdf} }
Kompella, V.R.; Luciw, M. & Schmidhuber, J.	2011	Incremental slow feature analysis [Abstract] [BibTeX] [URL(2)]	Twenty-Second International Joint Conference on Artificial Intelligence .	inproceedings
Abstract: The Slow Feature Analysis (SFA) unsupervised learning framework extracts features representing the underlying causes of the changes within a tem- porally coherent high-dimensional raw sensory in- put signal. We develop the first online version of SFA, via a combination of incremental Princi- pal Components Analysis and Minor Components Analysis. Unlike standard batch-based SFA, on- line SFA adapts along with non-stationary environ- ments, which makes it a generally useful unsuper- vised preprocessor for autonomous learning agents. We compare online SFA to batch SFA in several experiments and show that it indeed learns without a teacher to encode the input stream by informa- tive slow features representing meaningful abstract environmental properties. We extend online SFA to deep networks in hierarchical fashion, and use them to successfully extract abstract object position information from high-dimensional video.
BibTeX: @inproceedings{KompellaLuciwEtAl-2011, author = {Kompella, Varun Raj and Luciw, Matthew and Schmidhuber, Juergen}, title = {Incremental slow feature analysis}, booktitle = {Twenty-Second International Joint Conference on Artificial Intelligence}, year = {2011}, url2 = {http://ai2-s2-pdfs.s3.amazonaws.com/1aee/341fb6c82377731ad6a5004d71e2d2de62a7.pdf} }
Kompella, V.R.; Luciw, M. & Schmidhuber, J.	2011	Incremental slow feature analysis: adaptive and episodic learning from high-dimensional input streams [Abstract] [BibTeX] [URL]	e-print arXiv:1112.2113 .	misc
Abstract: Slow Feature Analysis (SFA) extracts features representing the underlying causes of changes within a temporally coherent high-dimensional raw sensory input signal. Our novel incremental version of SFA (IncSFA) combines incremental Principal Components Analysis and Minor Components Analysis. Unlike standard batch-based SFA, IncSFA adapts along with non-stationary environments, is amenable to episodic training, is not corrupted by outliers, and is covariance-free. These properties make IncSFA a generally useful unsupervised preprocessor for autonomous learning agents and robots. In IncSFA, the CCIPCA and MCA updates take the form of Hebbian and anti-Hebbian updating, extending the biological plausibility of SFA. In both single node and deep network versions, IncSFA learns to encode its input streams (such as high-dimensional video) by informative slow features representing meaningful abstract environmental properties. It can handle cases where batch SFA fails.
BibTeX: @misc{KompellaLuciwEtAl-2011a, author = {Kompella, Varun R and Luciw, Matthew and Schmidhuber, J{\"u}ergen}, title = {Incremental slow feature analysis: adaptive and episodic learning from high-dimensional input streams}, year = {2011}, howpublished = {e-print arXiv:1112.2113}, url = {https://arxiv.org/abs/1112.2113} }
Kompella, V.R.; Luciw, M. & Schmidhuber, J.	2012	Incremental slow feature analysis: adaptive low-complexity slow feature updating from high-dimensional input streams [Abstract] [BibTeX] [URL]	Neural Computation , 24(11), 2994-3024. Publ. MIT Press - Journals.	article
Abstract: We introduce here an incremental version of slow feature analysis (IncSFA), combining candid covariance-free incremental principal components analysis (CCIPCA) and covariance-free incremental minor components analysis (CIMCA). IncSFA's feature updating complexity is linear with respect to the input dimensionality, while batch SFA's (BSFA) updating complexity is cubic. IncSFA does not need to store, or even compute, any covariance matrices. The drawback to IncSFA is data efficiency: it does not use each data point as effectively as BSFA. But IncSFA allows SFA to be tractably applied, with just a few parameters, directly on high-dimensional input streams (e.g., visual input of an autonomous agent), while BSFA has to resort to hierarchical receptive-field-based architectures when the input dimension is too high. Further, IncSFA's updates have simple Hebbian and anti-Hebbian forms, extending the biological plausibility of SFA. Experimental results show IncSFA learns the same set of features as BSFA and can handle a few cases where BSFA fails.
BibTeX: @article{KompellaLuciwEtAl-2012, author = {Varun Raj Kompella and Matthew Luciw and J{\"{u}}rgen Schmidhuber}, title = {Incremental slow feature analysis: adaptive low-complexity slow feature updating from high-dimensional input streams}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2012}, volume = {24}, number = {11}, pages = {2994--3024}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00344}, doi = {http://doi.org/10.1162/NECO_a_00344} }
Kompella, V.R.; Luciw, M. & Schmidhuber, J.	2012	Hierarchical incremental slow feature analysis [BibTeX]	In Workshop on Deep Hierarchies in Vision .	inproceedings
BibTeX: @inproceedings{KompellaLuciwEtAl-2012b, author = {Kompella, Varun Raj and Luciw, Matthew and Schmidhuber, J{\"u}rgen}, title = {Hierarchical incremental slow feature analysis}, booktitle = {In Workshop on Deep Hierarchies in Vision}, year = {2012} }
Kompella, V.R.; Luciw, M.; Stollenga, M.; Pape, L. & Schmidhuber, J.	2012	Autonomous learning of abstractions using curiosity-driven modular incremental slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL) , 1-8. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: To autonomously learn behaviors in complex environments, vision-based agents need to develop useful sensory abstractions from high-dimensional video. We propose a modular, curiosity-driven learning system that autonomously learns multiple abstract representations. The policy to build the library of abstractions is adapted through reinforcement learning, and the corresponding abstractions are learned through incremental slow-feature analysis (IncSFA). IncSFA learns each abstraction based on how the inputs change over time, directly from unprocessed visual data. Modularity is induced via a gating system, which also prevents abstraction duplication. The system is driven by a curiosity signal that is based on the learnability of the inputs by the current adaptive module. After the learning completes, the result is multiple slow-feature modules serving as distinct behavior-specific abstractions. Experiments with a simulated iCub humanoid robot show how the proposed method effectively learns a set of abstractions from raw un-preprocessed video, to our knowledge the first curious learning agent to demonstrate this ability.
BibTeX: @inproceedings{KompellaLuciwEtAl-2012a, author = {Kompella, Varun Raj and Luciw, Matthew and Stollenga, Marijn and Pape, Leo and Schmidhuber, J{\"u}rgen}, title = {Autonomous learning of abstractions using curiosity-driven modular incremental slow feature analysis}, booktitle = {2012 {IEEE} International Conference on Development and Learning and Epigenetic Robotics ({ICDL})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2012}, pages = {1--8}, url = {http://ieeexplore.ieee.org/document/6400829/}, url2 = {http://www.idsia.ch/~luciw/papers/icdl12-kompella.pdf}, doi = {http://doi.org/10.1109/devlrn.2012.6400829} }
Kompella, V.R.; Luciw, M.; Stollenga, M.F. & Schmidhuber, J.	2016	Optimal curiosity-driven modular incremental slow feature analysis [Abstract] [BibTeX] [URL]	Neural Computation , 28(8), 1599-1662. Publ. MITP.	article
Abstract: Consider a self-motivated artificial agent who is exploring a complex environment. Part of the complexity is due to the raw high-dimensional sensory input streams, which the agent needs to make sense of. Such inputs can be compactly encoded through a variety of means; one of these is slow feature analysis (SFA). Slow features encode spatiotemporal regularities, which are information-rich explanatory factors (latent variables) underlying the high-dimensional input streams. In our previous work, we have shown how slow features can be learned incrementally, while the agent explores its world, and modularly, such that different sets of features are learned for different parts of the environment (since a single set of regularities does not explain everything). In what order should the agent explore the different parts of the environment? Following Schmidhuber’s theory of artificial curiosity, the agent should always concentrate on the area where it can learn the easiest-to-learn set of features that it has not already learned. We formalize this learning problem and theoretically show that, using our model, called curiosity-driven modular incremental slow feature analysis, the agent on average will learn slow feature representations in order of increasing learning difficulty, under certain mild conditions. We provide experimental results to support the theoretical analysis.
BibTeX: @article{KompellaLuciwEtAl-2016, author = {Kompella, Varun Raj and Luciw, Matthew and Stollenga, Marijn Frederik and Schmidhuber, Juergen}, title = {Optimal curiosity-driven modular incremental slow feature analysis}, journal = {Neural Computation}, publisher = {MITP}, year = {2016}, volume = {28}, number = {8}, pages = {1599--1662}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00855}, doi = {http://doi.org/10.1162/neco_a_00855} }
Kompella, V.R.; Pape, L.; Masci, J.; Frank, M. & Schmidhuber, J.	2011	AutoIncSFA and vision-based developmental learning for humanoid robots [Abstract] [BibTeX] [URL] [URL(2)]	2011 11^th IEEE-RAS International Conference on Humanoid Robots , 622-629. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Humanoids have to deal with novel, unsupervised high-dimensional visual input streams. Our new method Au- toIncSFA learns to compactly represent such complex sensory input sequences by very few meaningful features corresponding to high-level spatio-temporal abstractions, such as: a person is approaching me, or: an object was toppled. We explain the advantages of AutoIncSFA over previous related methods, and show that the compact codes greatly facilitate the task of a reinforcement learner driving the humanoid to actively explore its world like a playing baby, maximizing intrinsic curiosity reward signals for reaching states corresponding to previously unpredicted AutoIncSFA features.
BibTeX: @inproceedings{KompellaPapeEtAl-2011, author = {Kompella, Varun Raj and Pape, Leo and Masci, Jonathan and Frank, Mikhail and Schmidhuber, J{\"u}rgen}, title = {{AutoIncSFA} and vision-based developmental learning for humanoid robots}, booktitle = {2011 11\textsuperscript{th} {IEEE}-{RAS} International Conference on Humanoid Robots}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {622--629}, url = {http://ieeexplore.ieee.org/document/6100865/}, url2 = {https://pdfs.semanticscholar.org/380f/32bb5dbce7d93b607533d5870d41b25e95b4.pdf}, doi = {http://doi.org/10.1109/humanoids.2011.6100865} }
Kompella, V.R.; Stollenga, M.; Luciw, M. & Schmidhuber, J.	2017	Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots [Abstract] [BibTeX] [URL]	Artificial Intelligence , 247, -. Publ. Elsevier.	article
Abstract: In the absence of external guidance, how can a robot learn to map the many raw pixels of high-dimensional visual inputs to useful action sequences? We propose here Continual Curiosity driven Skill Acquisition (CCSA). CCSA\ makes robots intrinsically motivated to acquire, store and reuse skills. Previous curiosity-based agents acquired skills by associating intrinsic rewards with world model improvements, and used reinforcement learning to learn how to get these intrinsic rewards. CCSA\ also does this, but unlike previous implementations, the world model is a set of compact low-dimensional representations of the streams of high-dimensional visual information, which are learned through incremental slow feature analysis. These representations augment the robot's state space with new information about the environment. We show how this information can have a higher-level (compared to pixels) and useful interpretation, for example, if the robot has grasped a cup in its field of view or not. After learning a representation, large intrinsic rewards are given to the robot for performing actions that greatly change the feature output, which has the tendency otherwise to change slowly in time. We show empirically what these actions are (e.g., grasping the cup) and how they can be useful as skills. An acquired skill includes both the learned actions and the learned slow feature representation. Skills are stored and reused to generate new observations, enabling continual acquisition of complex skills. We present results of experiments with an iCub humanoid robot that uses CCSA\ to incrementally acquire skills to topple, grasp and pick-place a cup, driven by its intrinsic motivation from raw pixel vision.
BibTeX: @article{KompellaStollengaEtAl-2017, author = {Varun Raj Kompella and Marijn Stollenga and Matthew Luciw and Juergen Schmidhuber}, title = {Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots}, journal = {Artificial Intelligence}, publisher = {Elsevier}, year = {2017}, volume = {247}, pages = {-}, url = {http://www.sciencedirect.com/science/article/pii/S000437021500017X}, doi = {http://doi.org/10.1016/j.artint.2015.02.001} }
Kompella, V.R.; Stollenga, M.F.; Luciw, M.D. & Schmidhuber, J.	2014	Explore to see, learn to perceive, get the actions for free: SKILLABILITY [Abstract] [BibTeX] [URL] [URL(2)]	2014 International Joint Conference on Neural Networks (IJCNN) , 2705-2712.	inproceedings
Abstract: How can a humanoid robot autonomously learn and refine multiple sensorimotor skills as a byproduct of curiosity driven exploration, upon its high-dimensional unprocessed visual input? We present SKILLABILITY, which makes this possible. It combines the recently introduced Curiosity Driven Modular Incremental Slow Feature Analysis (Curious Dr. MISFA) with the well-known options framework. Curious Dr. MISFA's objective is to acquire abstractions as quickly as possible. These abstractions map high-dimensional pixel-level vision to a low-dimensional manifold. We find that each learnable abstraction augments the robot's state space (a set of poses) with new information about the environment, for example, when the robot is grasping a cup. The abstraction is a function on an image, called a slow feature, which can effectively discretize a high-dimensional visual sequence. For example, it maps the sequence of the robot watching its arm as it moves around, grasping randomly, then grasping a cup, and moving around some more while holding the cup, into a step function having two outputs: when the cup is or is not currently grasped. The new state space includes this grasped/not grasped information. Each abstraction is coupled with an option. The reward function for the option's policy (learned through Least Squares Policy Iteration) is high for transitions that produce a large change in the step-functionlike slow features. This corresponds to finding bottleneck states, which are known good subgoals for hierarchical reinforcement learning - in the example, the subgoal corresponds to grasping the cup. The final skill includes both the learned policy and the learned abstraction. SKILLABILITY makes our iCub the first humanoid robot to learn complex skills such as to topple or grasp an object, from raw high-dimensional video input, driven purely by its intrinsic motivations.
BibTeX: @inproceedings{KompellaStollengaEtAl-2014, author = {Kompella, Varan R and Stollenga, Marijn F and Luciw, Matthew D and Schmidhuber, Juergen}, title = {Explore to see, learn to perceive, get the actions for free: {SKILLABILITY}}, booktitle = {2014 International Joint Conference on Neural Networks (IJCNN)}, year = {2014}, pages = {2705--2712}, url = {http://ieeexplore.ieee.org/document/6889784/?arnumber=6889784}, url2 = {http://people.idsia.ch/~kompella/Papers/IJCNN_14.pdf}, doi = {http://doi.org/10.1109/ijcnn.2014.6889784} }
Kompella, V.R. & Wiskott, L.	2017	Intrinsically Motivated Acquisition of Modular Slow Features for Humanoids in Continuous and Non-Stationary Environments [BibTeX]	CoRR , abs/1701.04663.	article
BibTeX: @article{KompellaWiskott-2017, author = {Varun Raj Kompella and Laurenz Wiskott}, title = {Intrinsically Motivated Acquisition of Modular Slow Features for Humanoids in Continuous and Non-Stationary Environments}, journal = {CoRR}, year = {2017}, volume = {abs/1701.04663} }
Konen, W.	2009	On the numeric stability of the SFA implementation sfa-tk [Abstract] [BibTeX] [URL] [URL(2)]	e-print arXiv:0912.1064 .	misc
Abstract: Slow feature analysis (SFA) is a method for extracting slowly varying features from a quickly varying multidimensional signal. An open source Matlab-implementation sfa-tk makes SFA easily useable. We show here that under certain circumstances, namely when the covariance matrix of the nonlinearly expanded data does not have full rank, this implementation runs into numerical instabilities. We propse a modified algorithm based on singular value decomposition (SVD) which is free of those instabilities even in the case where the rank of the matrix is only less than 10% of its size. Furthermore we show that an alternative way of handling the numerical problems is to inject a small amount of noise into the multidimensional input signal which can restore a rank-deficient covariance matrix to full rank, however at the price of modifying the original data and the need for noise parameter tuning.
BibTeX: @misc{Konen-2009, author = {Konen, Wolfgang}, title = {On the numeric stability of the {SFA} implementation sfa-tk}, year = {2009}, howpublished = {e-print arXiv:0912.1064}, url = {https://arxiv.org/abs/0912.1064}, url2 = {http://www.gm.fh-koeln.de/~konen/Publikationen/arXiv2009-SVD_SFA.pdf} }
Konen, W.	2011	Self-configuration from a machine-learning perspective [Abstract] [BibTeX] [URL]	e-print arXiv:1105.1951 .	misc
Abstract: The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for machine learning (e.g. data mining or board games), most applications beyond the level of toy problems need careful hand-tuning or human ingenuity (i.e. detection of interesting patterns) or both. We discuss several aspects how self-configuration can help to alleviate these problems. One aspect is the self-configuration by tuning of algorithms, where recent advances have been made in the area of SPO (Sequen- tial Parameter Optimization). Another aspect is the self-configuration by pattern detection or feature construction. Forming multiple features (e.g. random boolean functions) and using algorithms (e.g. random forests) which easily digest many fea- tures can largely increase learning speed. However, a full-fledged theory of feature construction is not yet available and forms a current barrier in machine learning. We discuss several ideas for systematic inclusion of feature construction. This may lead to partly self-configuring machine learning solutions which show robustness, flexibility, and fast learning in potentially changing environments.
BibTeX: @misc{Konen-2011, author = {Konen, Wolfgang}, title = {Self-configuration from a machine-learning perspective}, year = {2011}, howpublished = {e-print arXiv:1105.1951}, url = {https://arxiv.org/abs/1105.1951} }
Konen, W.	2011	Der SFA-Algorithmus für Klassifikation [Abstract] [BibTeX] [URL(2)]	CIOP Report, Cologne University of Applied Sciences, Cologne University of Applied Sciences (08/11).	techreport
Abstract: Dieser Technische Report fasst den SFA-Algorithmus für Klassifikation zusammen, wie er im MATLAB-Paket sfa-tk ab Version V2.6 (aktuelle Version V2.8) 1 implementiert ist.
BibTeX: @techreport{Konen-2011a, author = {Konen, Wolfgang}, title = {Der {SFA-A}lgorithmus f{\"u}r {K}lassifikation}, school = {Cologne University of Applied Sciences}, year = {2011}, number = {08/11}, url2 = {https://www.researchgate.net/profile/Wolfgang_Konen/publication/235709834_Der_SFA-Algorithmus_fur_Klassifikation/links/55f740ae08aeafc8abfd52fb.pdf} }
Konen, W.	2012	SFA classification with few training data: improvements with parametric bootstrap [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Slow Feature Analysis (SFA) is a versatile algorithm to nd stable features or slow- varying signals in multidimensional data. It is capable of nding highly relevant features for classi cation tasks. This paper deals with the marginal training data problem which appears in SFA classi cation when the number of training records is too low. We derive a quantitative condition between training set size and SFA con guration parameters which allows to predict whether the marginal training data problem will occur. We analyze the reasons for the problem and propose several strategies to avoid it. Among these strategies, the parametric bootstrap approach, which augments the training data with virtual training patterns drawn from an estimated distribution, successfully solves the marginal training data problem. We report rst evidence, that parametric bootstrap is also bene cial for non-marginal SFA and for other machine learning algorithms like Random Forests.
BibTeX: @misc{Konen-2012, author = {Konen, Wolfgang}, title = {{SFA} classification with few training data: improvements with parametric bootstrap}, year = {2012}, url2 = {https://www.researchgate.net/profile/Wolfgang_Konen/publication/235709835_SFA_classification_with_few_training_data_Improvements_with_parametric_bootstrap/links/55f7416008ae07629dc357ff.pdf} }
Konen, W. & Koch, P.	2010	How slow is slow? SFA detects signals that are slower than the driving force [Abstract] [BibTeX] [URL(2)]	Proc. 4^th Int. Conf. on Bioinspired Optimization Methods and their Applications, BIOMA, Ljubljana, Slovenia . Ed. Filipic, B. & Silc, J.	inproceedings
Abstract: Slow feature analysis (SFA) is a bioinspired method for extracting slowly varying driving forces from quickly varying nonstationary time series. We show here that it is possible for SFA to detect a component which is even slower than the driving force itself (e.g. the envelope of a modulated sine wave). It depends on circumstances like the embedding dimension, the time series predictability, or the base frequency, whether the driving force itself or a slower subcomponent is detected. Interestingly, we observe a swift phase transition from one regime to another and it is the objective of this work to quantify the influence of various parameters on this phase transition. We conclude that what is perceived as slow by SFA varies and that a more or less fast switching from one regime to another occurs, perhaps showing some similarity to human perception.
BibTeX: @inproceedings{KonenKoch-2010, author = {Wolfgang Konen and Patrick Koch}, title = {How slow is slow? {SFA} detects signals that are slower than the driving force}, booktitle = {Proc. 4\textsuperscript{th} Int. Conf. on Bioinspired Optimization Methods and their Applications, BIOMA, Ljubljana, Slovenia}, year = {2010}, url2 = {http://www.gm.fh-koeln.de/~konen/Publikationen/BIOMA10-howslow.pdf} }
Konen, W. & Koch, P.	2009	How slow is slow? SFA detects signals that are slower than the driving force [Abstract] [BibTeX] [URL] [URL(2)]	e-print arXiv:0911.4397 .	misc
Abstract: Slow feature analysis (SFA) is a method for extracting slowly varying driving forces from quickly varying nonstationary time series. We show here that it is possible for SFA to detect a component which is even slower than the driving force itself (e.g. the envelope of a modulated sine wave). It is shown that it depends on circumstances like the embedding dimension, the time series predictability, or the base frequency, whether the driving force itself or a slower subcomponent is detected. We observe a phase transition from one regime to the other and it is the purpose of this work to quantify the influence of various parameters on this phase transition. We conclude that what is percieved as slow by SFA varies and that a more or less fast switching from one regime to the other occurs, perhaps showing some similarity to human perception.
BibTeX: @misc{KonenKoch-2009, author = {Konen, Wolfgang and Koch, Patrick}, title = {How slow is slow? {SFA} detects signals that are slower than the driving force}, year = {2009}, howpublished = {e-print arXiv:0911.4397}, url = {https://arxiv.org/abs/0911.4397v1}, url2 = {http://www.gm.fh-koeln.de/~konen/Publikationen/arXiv2009-slow.pdf} }
Konen, W. & Koch, P.	2011	The slowness principle: SFA can detect different slow components in nonstationary time series [Abstract] [BibTeX] [URL] [URL(2)]	International Journal of Innovative Computing and Applications (IJICA) , 3(1), 3-10. Publ. Inderscience Publishers.	article
Abstract: Slow feature analysis (SFA) is a bioinspired method for extracting slowly varying driving forces from quickly varying non-stationary time series. We show here that it is possible for SFA to detect a component which is even slower than the driving force itself (e.g., the envelope of a modulated sine wave). It depends on circumstances like the embedding dimension, the time series predictability, or the base frequency, whether the driving force itself or a slower subcomponent is detected. Interestingly, we observe a swift phase transition from one regime to another and it is the objective of this work to quantify the influence of various parameters on this phase transition. We conclude that what is perceived as slow by SFA varies and that a more or less fast switching from one regime to another occurs, perhaps showing some similarity to human perception.
BibTeX: @article{KonenKoch-2011, author = {Wolfgang Konen and Patrick Koch}, title = {The slowness principle: {SFA} can detect different slow components in nonstationary time series}, journal = {International Journal of Innovative Computing and Applications (IJICA)}, publisher = {Inderscience Publishers}, year = {2011}, volume = {3}, number = {1}, pages = {3--10}, url = {http://www.inderscience.com/offer.php?id=37946}, url2 = {http://www.gm.fh-koeln.de/~konen/Publikationen/IJICA2010-howslow.pdf}, doi = {http://doi.org/10.1504/ijica.2011.037946} }
Konen, W.; Zaefferer, M.; Koch, P. & Kumar, P.J.	2014	Package ‘rSFA’ [Abstract] [BibTeX] [URL]	.	misc
Abstract: No abstract.
BibTeX: @misc{KonenZaeffererEtAl-2014, author = {Konen, Wolfgang and Zaefferer, Martin and Koch, Patrick and Kumar, Prawyn Jebakumar}, title = {Package {\textquoteleft}{rSFA}{\textquoteright}}, year = {2014}, url = {http://www.et.bs.ehu.es/cran/web/packages/rSFA/rSFA.pdf} }
Kramer, O.	2010	Computational intelligence and sustainable energy: case studies and applications [Abstract] [BibTeX] [URL]	TR-10-010, International Computer Science Institute Berkley University, TR-10-010, International Computer Science Institute Berkley University .	techreport
Abstract: Sustainability is of great importance due to increasing demands and limited resources. Many problem classes in sustainable energy systems are data mining, optimization, and control tasks. In this work we demonstrate how techniques from computational intelligence can help in solving important tasks in sustainable energy systems. We will show how statistically sound wind models can be estimated with kernel smoothing methods. Radial basis functions will be employed for wind resource visualization. Support vector machines turn out to be successful in forecasting wind energy. Monitoring of high-dimensional wind time series is possible with a self-organizing map approach. Slow driving features in wind time series can be detected with slow feature analysis. Last, we will demonstrate how a learning classifier system evolves control rules for a virtual power plant with a simple demand side management model.
BibTeX: @techreport{Kramer-2010, author = {Kramer, Oliver}, title = {Computational intelligence and sustainable energy: case studies and applications}, school = {TR-10-010, International Computer Science Institute Berkley University}, year = {2010}, url = {http://www.icsi.berkeley.edu/pubs/techreports/TR-10-010.pdf} }
Kramer, O. & Hein, T.	2011	Monitoring of multivariate wind resources with self-organizing maps and slow feature analysis [Abstract] [BibTeX] [URL]	2011 IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG) , 1-8. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Wind power is an important part of a sustainable and smart energy grid. Wind energy production datasets from hundreds of wind farms and thousands of windmills are collected, and have to be analyzed and understood. As wind is a volatile energy source, state observation has an important part to play for grid management, fault analysis and planning strategies of grid operators. We demonstrate how two approaches from unsupervised neural computation help to understand high-dimensional wind resource time series. The first approach for visualization of multivariate sequences is based on self-organizing feature maps. The output sequence allows the monitoring of the overall system state with a low-dimensional linear visualization that reflects the topological characteristics of the original wind data. We demonstrate the visualization on real-world wind resource measurements. The second approach shows how to identify the slowest feature in a multivariate wind time series, also known as driving force, with the help of slow feature analysis. Experiments, parameter analyses, and first interpretations demonstrate the capabilities of the approaches.
BibTeX: @inproceedings{KramerHein-2011, author = {Oliver Kramer and Tobias Hein}, title = {Monitoring of multivariate wind resources with self-organizing maps and slow feature analysis}, booktitle = {2011 {IEEE} Symposium on Computational Intelligence Applications In Smart Grid ({CIASG})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {1--8}, url = {http://ieeexplore.ieee.org/document/5953327/}, doi = {http://doi.org/10.1109/ciasg.2011.5953327} }
Kreitmann, P.	2010	Action recognition in video [Abstract] [BibTeX] [URL] [URL(2)]	. Publ. Citeseer.	misc
Abstract: Automatic action recognition in video has a broad array of applications, from surveillance to interactive video games. Classic algorithms usually use hand- crafted descriptors such as SIFT (see [5]) or HOG (see [3]) to compute feature vectors of videos, and have achieved promising results in the past (see [7]). More recently, Quoc Le and Will Zou at the Stanford AI lab have proved that ISA features obtained from unsupervised learning achieve higher performance, while being much faster to engineer that hand-crafted features (their work is not yet published). SFA features have achieved good results in object recognition as well as position and rotation extraction from artificial video signal (see [4]). In this work, we experiment using SFA features for action recognition.
BibTeX: @misc{Kreitmann-2010, author = {Kreitmann, Pierre}, title = {Action recognition in video}, publisher = {Citeseer}, year = {2010}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.375.1808&rep=rep1&type=pdf}, url2 = {https://pdfs.semanticscholar.org/2a50/f15e0b7c7170b9c4de67a36944a91b6bd20c.pdf} }
Kühnl, T.	2013	Road terrain detection for advanced driver assistance systems [Abstract] [BibTeX] [URL(2)]	Bielefeld, Universität Bielefeld, Diss., 2013, Bielefeld, Universität Bielefeld, Diss., 2013 .	phdthesis
Abstract: In recent years, automotive manufacturers have equipped their vehicles with in- novative Advanced Driver Assistance Systems (ADAS) to ease driving and avoid dangerous situations, such as unintended lane departures or collisions with other road users, like vehicles and pedestrians. To this end, ADAS at the cutting edge are equipped with cameras to sense the vehicle surrounding. An important source of information for future ADAS is the road course, i.e., the future driving path of the ego-vehicle and other vehicles. Therefore, this thesis focuses on the camera-based analysis of road scenes and the detection of important types of road terrain, such as road area and ego-lane, which are necessary to draw inference about the actual road course and potential space for evasion maneuvers. For this purpose, this thesis presents a generic concept for the visual and spatial analysis of the road environment. The core of the proposed method is a hierarchical feature extraction that combines local visual appearance with its spatial layout. In this sense, a novel vision-based approach for road terrain detection that goes beyond classical lane marking detection and image segmentation approaches is presented. Thus, the approach enhances the ability to cope with noise and appearance changes because the classification decision is not only based on local visual appearance but on a combination of visual and spatial aspects. This results in a higher robustness under various visual conditions due to different asphalt appearance, illumination changes, and shadows. The approach’s generic architecture internally represents certain visual proper- ties, such as road area, road boundary, and lane marking information by means of a visuospatial representation. In contrast to many related approaches for road terrain detection, the proposed method does not employ an explicit road course model. Instead, the method learns classifying road terrain based on a combination of visual and spatial features by using machine learning. Especially the discrimina- tion between ego-lane and other parts of the road area is very challenging, because a distinction based on local appearance is impossible. Extensive evaluations in urban scenarios show that the proposed system functions in spatially diverse road scenes and reliably detects ego-lane and road area even in challenging situations. Those situations may comprise bad-quality or missing lane markings, curbstones delimiting the road, and occlusion of lane delimiters, e.g., caused by parked cars. Furthermore, the generic concept does not only have advantages in road terrain detection, but also in many other applications, benefitting from visual and spatial scene analysis. In order to prove this, the method is applied for pure vision-based ego-vehicle localization on the lane level. In this regard, a reliable classification allowing an inference about how many lanes exist adjacent to the ego-lane is pre- sented on a large highway dataset. In summary, this thesis presents a generic concept for visual and spatial anal- ysis of the road environment and is therefore a substantial contribution to the development of future ADAS. Towards this end, the general approach is geared to problem-solving for complex situations that can not be handled by state-of-the-art methods, which has been shown for inner-city road terrain detection and ego-vehicle localization.
BibTeX: @phdthesis{Kuehnl-2013, author = {K{\"u}hnl, Tobias}, title = {Road terrain detection for advanced driver assistance systems}, school = {Bielefeld, Universit{\"a}t Bielefeld, Diss., 2013}, year = {2013}, url2 = {https://pub.uni-bielefeld.de/download/2633277/2633278} }
Kuhnl, T.; Kummert, F. & Fritsch, J.	2011	Monocular road segmentation using slow feature analysis [Abstract] [BibTeX] [URL]	2011 IEEE Intelligent Vehicles Symposium (IV) , 800-806. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: In this paper a novel approach for road detection with a monocular camera is introduced. We propose a two step approach, combining a patch-based segmentation with additional boundary detection. We use Slow Feature Analysis (SFA) which leads to improved appearance descriptors for road and non-road parts on patch level. From the slow features a low order feature set is formed which is used together with color and Walsh Hadamard texture features to train a patch-based GentleBoost classifier. This allows extracting areas from the image that correspond to the road with a certain confidence. Typically the border regions between road and non-road have the highest classification error rates, because the appearance is hard to distinguish on the patch level. Therefore we propose a post-processing step with a specialized classifier applied to the boundary region of the image to improve the segmentation results. In order to evaluate the quality of road segmentation we propose an application-based quality measurement applying an inverse perspective mapping on the image to obtain a Birds Eye View (BEV). The advantage of this approach is that the important distant parts and boundaries of the road in the real world, which are only a low fraction in the perspective image, can be assessed in this metric measure significantly better than on the pixel level. In addition, we estimate the driving corridor width and boundary error, because for Advanced Driver Assistant Systems (ADAS) metric information is needed. For all evaluations in different road and weather conditions, our system shows an improved performance of the two step approach compared to the basic segmentation.
BibTeX: @inproceedings{KuhnlKummertEtAl-2011, author = {Tobias Kuhnl and Franz Kummert and Jannik Fritsch}, title = {Monocular road segmentation using slow feature analysis}, booktitle = {2011 {IEEE} Intelligent Vehicles Symposium ({IV})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {800--806}, url = {http://ieeexplore.ieee.org/document/5940416/}, doi = {http://doi.org/10.1109/ivs.2011.5940416} }
Kühnl, T.; Kummert, F. & Fritsch, J.	2013	Visual ego-vehicle lane assignment using spatial ray features [Abstract] [BibTeX] [URL] [URL(2)]	Intelligent Vehicles Symposium (IV), 2013 IEEE , 1101-1106.	inproceedings
Abstract: Assigning the ego-vehicle to a lane is not only beneficial for navigation but will be an essential element in future Advanced Driver Assistance Systems. This paper describes an approach for ego-lane index estimation using only a monocular camera and no additional sensing equipment like, e.g., the typically employed GPS and Inertial Measurement Unit. Key aspect of the approach are SPatial RAY (SPRAY) features which represent the spatial layout of the road in the visual scene. The proposed method perceives a variety of local visual properties of the scene by means of base classifiers operating on patches extracted from camera images. The spatial arrangement of these local visual properties are captured using SPRAY features. With a boosting classifier trained on these features the ego-lane index is obtained. The system is evaluated on low traffic density and complementary to an object-based approach suitable for heavy traffic. In the conducted experiments, the proposed approach reaches recognition rates of 93% to 97% on individual highway images without applying any kind of temporal filtering.
BibTeX: @inproceedings{KuehnlKummertEtAl-2013, author = {K{\"{u}}hnl, Tobias and Kummert, Franz and Fritsch, Jannik}, title = {Visual ego-vehicle lane assignment using spatial ray features}, booktitle = {Intelligent Vehicles Symposium (IV), 2013 IEEE}, year = {2013}, pages = {1101--1106}, url = {http://ieeexplore.ieee.org/document/6629613/}, url2 = {https://www.researchgate.net/profile/Jannik_Fritsch/publication/239949497_Visual_Ego-Vehicle_Lane_Assignment_using_Spatial_Ray_Features/links/00b7d51c401de9943a000000.pdf}, doi = {http://doi.org/10.1109/ivs.2013.6629613} }
Lefakis, L. & Fleuret, F.	2014	Dynamic programming boosting for discriminative macro-action discovery. [BibTeX] [URL(2)]	ICML , 1548-1556.	inproceedings
BibTeX: @inproceedings{LefakisFleuret-2014, author = {Lefakis, Leonidas and Fleuret, Francois}, title = {Dynamic programming boosting for discriminative macro-action discovery.}, booktitle = {ICML}, year = {2014}, pages = {1548--1556}, url2 = {https://pdfs.semanticscholar.org/18d6/187c6222336c2c0b1e23793f72a00f9700a5.pdf} }
Legenstein, R.; Wilbert, N. & Wiskott, L.	2010	Reinforcement learning on slow features of high-dimensional input streams. [Abstract] [BibTeX] [URL] [URL(2)]	PLoS Comput Biol , 6(8), e1000894. Publ. Public Library of Science.	article
Abstract: Humans and animals are able to learn complex behaviors based on a massive stream of sensory information from different modalities. Early animal studies have identified learning mechanisms that are based on reward and punishment such that animals tend to avoid actions that lead to punishment whereas rewarded actions are reinforced. However, most algorithms for reward-based learning are only applicable if the dimensionality of the state-space is sufficiently small or its structure is sufficiently simple. Therefore, the question arises how the problem of learning on high-dimensional data is solved in the brain. In this article, we propose a biologically plausible generic two-stage learning system that can directly be applied to raw high-dimensional input streams. The system is composed of a hierarchical slow feature analysis (SFA) network for preprocessing and a simple neural network on top that is trained based on rewards. We demonstrate by computer simulations that this generic architecture is able to learn quite demanding reinforcement learning tasks on high-dimensional visual input streams in a time that is comparable to the time needed when an explicit highly informative low-dimensional state-space representation is given instead of the high-dimensional visual input. The learning speed of the proposed architecture in a task similar to the Morris water maze task is comparable to that found in experimental studies with rats. This study thus supports the hypothesis that slowness learning is one important unsupervised learning principle utilized in the brain to form efficient state representations for behavioral learning.
BibTeX: @article{LegensteinWilbertEtAl-2010, author = {Robert Legenstein and Niko Wilbert and Laurenz Wiskott}, title = {Reinforcement learning on slow features of high-dimensional input streams.}, journal = {PLoS Comput Biol}, publisher = {Public Library of Science}, year = {2010}, volume = {6}, number = {8}, pages = {e1000894}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000894}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/LegensteinWilbertEtAl-2010-PLoSCompBiol.pdf}, doi = {http://doi.org/10.1371/journal.pcbi.1000894} }
Li, D.; Zhang, Z. & Tan, T.	2017	Large-Scale Slow Feature Analysis Using Spark for Visual Object Recognition [BibTeX]	CCF Chinese Conference on Computer Vision , 132-142.	inproceedings
BibTeX: @inproceedings{LiZhangEtAl-2017, author = {Li, Da and Zhang, Zhang and Tan, Tieniu}, title = {Large-Scale Slow Feature Analysis Using Spark for Visual Object Recognition}, booktitle = {CCF Chinese Conference on Computer Vision}, year = {2017}, pages = {132--142}, doi = {http://doi.org/10.1007/978-981-10-7305-2_12} }
Li, Z. & Yan, X.	2019	Complex dynamic process monitoring method based on slow feature analysis model of multi-subspace partitioning [Abstract] [BibTeX] [URL]	ISA Transactions , 95, 68-81.	article
Abstract: This study presents an ensemble monitoring strategy based on slow feature analysis (SFA) model of multi-subspace partitioning for dynamic large-scale process. SFA can effectively extract the various dynamics of process data, where the relationship between process data and slow features (SFs) can be revealed by transformation matrix. The similar projecting directions represent similar importance of variables, and corresponding latent variables (LVs) will show similar monitoring behavior. Several LV subspaces are obtained by dividing the transformation vectors with higher similarity into the same sub-block automatically based on the defined process variable related index and hierarchical clustering, which can avoid the problems of information loss and the selection of SFs. Then, the S2 statistics constructed in each subspaces are integrated by support vector data description to show an intuitive detection results. Experiments on Tennessee Eastman benchmark process and wastewater treatment process have validated the proposed strategy’s effectiveness and excellence.
BibTeX: @article{LI201968, author = {Zhichao Li and Xuefeng Yan}, title = {Complex dynamic process monitoring method based on slow feature analysis model of multi-subspace partitioning}, journal = {ISA Transactions}, year = {2019}, volume = {95}, pages = {68-81}, url = {https://www.sciencedirect.com/science/article/pii/S0019057819302356}, doi = {http://doi.org/10.1016/j.isatra.2019.05.013} }
Lies, J.-P.; Häfner, R.M. & Bethge, M.	2014	Slowness and sparseness have diverging effects on complex cell learning [Abstract] [BibTeX] [URL]	PLoS Comput Biol , 10(3), e1003468. Publ. Public Library of Science.	article
Abstract: Following earlier studies which showed that a sparse coding principle may explain the receptive field properties of complex cells in primary visual cortex, it has been concluded that the same properties may be equally derived from a slowness principle. In contrast to this claim, we here show that slowness and sparsity drive the representations towards substantially different receptive field properties. To do so, we present complete sets of basis functions learned with slow subspace analysis (SSA) in case of natural movies as well as translations, rotations, and scalings of natural images. SSA directly parallels independent subspace analysis (ISA) with the only difference that SSA maximizes slowness instead of sparsity. We find a large discrepancy between the filter shapes learned with SSA and ISA. We argue that SSA can be understood as a generalization of the Fourier transform where the power spectrum corresponds to the maximally slow subspace energies in SSA. Finally, we investigate the trade-off between slowness and sparseness when combined in one objective function.
BibTeX: @article{LiesHaefnerEtAl-2014a, author = {Lies, J{\"o}rn-Philipp and H{\"a}fner, Ralf M and Bethge, Matthias}, title = {Slowness and sparseness have diverging effects on complex cell learning}, journal = {PLoS Comput Biol}, publisher = {Public Library of Science}, year = {2014}, volume = {10}, number = {3}, pages = {e1003468}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1003468}, doi = {http://doi.org/10.1371/journal.pcbi.1003468} }
Liwicki, S.	2014	Robust online subspace learning [Abstract] [BibTeX] [URL]	Imperial College, Imperial College .	phdthesis
Abstract: In this thesis, I aim to advance the theories of online non-linear subspace learning through the development of strategies which are both efficient and robust. The use of sub- space learning methods is very popular in computer vision and they have been employed to numerous tasks. With the increasing need for real-time applications, the formulation of online (i.e. incremental and real-time) learning methods is a vibrant research field and has received much attention from the research community. A major advantage of incre- mental systems is that they update the hypothesis during execution, thus allowing for the incorporation of the real data seen in the testing phase. Tracking acts as an attractive and popular evaluation tool for incremental systems, and thus, the connection between online learning and adaptive tracking is seen commonly in the literature. The proposed system in this thesis facilitates learning from noisy input data, e.g. caused by occlusions, casted shadows and pose variations, that are challenging problems in general tracking frameworks. First, a fast and robust alternative to standard l 2 -norm principal component analysis (PCA) is introduced, which I coin Euler PCA (e-PCA). The formulation of e-PCA is based on robust, non-linear kernel PCA (KPCA) with a cosine-based kernel function that is expressed via an explicit feature space. When applied to tracking, face reconstruction and background modeling, promising results are achieved. In the second part, the problem of matching vectors of 3D rotations is explicitly targeted. A novel distance which is robust for 3D rotations is introduced, and formulated as a kernel function. The kernel leads to a new representation of 3D rotations, the full-angle quaternion (FAQ) representation. Finally, I propose 3D object recognition from point clouds, and object tracking with color values using FAQs. A domain-specific kernel function designed for visual data is then presented. KPCA with Krein space kernels is introduced, as this kernel is indefinite, and an exact incre- mental learning framework for the new kernel is developed. In a tracker framework, the presented online learning outperforms the competitors in nine popular and challenging video sequences. In the final part, the generalized eigenvalue problem is studied. Specifically, incre- mental slow feature analysis (SFA) with indefinite kernels is proposed, and applied to temporal video segmentation and tracking with change detection. As online SFA allows for drift detection, further improvements are achieved in the evaluation of the tracking task.
BibTeX: @phdthesis{Liwicki-2014, author = {Liwicki, Stephan}, title = {Robust online subspace learning}, school = {Imperial College}, year = {2014}, url = {https://spiral.imperial.ac.uk/bitstream/10044/1/23234/1/Liwicki-S-2015-PhD-Thesis.pdf} }
Liwicki, S.; Zafeiriou, S. & Pantic, M.	2013	Incremental slow feature analysis with indefinite kernel for online temporal video segmentation [Abstract] [BibTeX] [URL]	Computer Vision - ACCV 2012 , Lecture Notes in Computer Science , 7725, 162-176. Eds. Lee, K.; Matsushita, Y.; Rehg, J. & Hu, Z. Publ. Springer Berlin Heidelberg.	incollection
Abstract: Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domain-specific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.
BibTeX: @incollection{LiwickiZafeiriouEtAl-2013, author = {Liwicki, Stephan and Zafeiriou, Stefanos and Pantic, Maja}, title = {Incremental slow feature analysis with indefinite kernel for online temporal video segmentation}, booktitle = {Computer Vision -- ACCV 2012}, publisher = {Springer Berlin Heidelberg}, year = {2013}, volume = {7725}, pages = {162--176}, url = {http://link.springer.com/chapter/10.1007/978-3-642-37444-9_13}, doi = {http://doi.org/10.1007/978-3-642-37444-9_13} }
Liwicki, S.; Zafeiriou, S. & Pantic, M.	2012	Incremental slow feature analysis with indefinite kernel for online temporal video segmentation [Abstract] [BibTeX] [URL] [URL(2)]	Asian Conference on Computer Vision , 162-176. Publ. Springer Nature.	inproceedings
Abstract: Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.
BibTeX: @inproceedings{LiwickiZafeiriouEtAl-2012, author = {Liwicki, Stephan and Zafeiriou, Stefanos and Pantic, Maja}, title = {Incremental slow feature analysis with indefinite kernel for online temporal video segmentation}, booktitle = {Asian Conference on Computer Vision}, publisher = {Springer Nature}, year = {2012}, pages = {162--176}, url = {http://link.springer.com/chapter/10.1007/978-3-642-37444-9_13}, url2 = {https://pdfs.semanticscholar.org/41af/863c5e1d3c5758e61b94dce05d1acdaff663.pdf}, doi = {http://doi.org/10.1007/978-3-642-37444-9_13} }
Liwicki, S.; Zafeiriou, S.P. & Pantic, M.	2015	Online kernel slow feature analysis for temporal video segmentation and tracking [Abstract] [BibTeX] [URL] [URL(2)]	IEEE transactions on image processing , 24(10), 2955-2970. Publ. IEEE.	article
Abstract: Slow feature analysis (SFA) is a dimensionality reduction technique which has been linked to how visual brain cells work. In recent years, the SFA was adopted for computer vision tasks. In this paper, we propose an exact kernel SFA (KSFA) framework for positive definite and indefinite kernels in Krein space. We then formulate an online KSFA which employs a reduced set expansion. Finally, by utilizing a special kind of kernel family, we formulate exact online KSFA for which no reduced set is required. We apply the proposed system to develop a SFA-based change detection algorithm for stream data. This framework is employed for temporal video segmentation and tracking. We test our setup on synthetic and real data streams. When combined with an online learning tracking system, the proposed change detection approach improves upon tracking setups that do not utilize change detection.
BibTeX: @article{LiwickiZafeiriouEtAl-2015, author = {Liwicki, Stephan and Zafeiriou, Stefanos P and Pantic, Maja}, title = {Online kernel slow feature analysis for temporal video segmentation and tracking}, journal = {IEEE transactions on image processing}, publisher = {IEEE}, year = {2015}, volume = {24}, number = {10}, pages = {2955--2970}, url = {http://ieeexplore.ieee.org/document/7097728/}, url2 = {https://pdfs.semanticscholar.org/d7fc/3940b948ba25ccf9b729cf8eeea3d2541da0.pdf}, doi = {http://doi.org/10.1109/TIP.2015.2428052} }
Loo, C. & Bardia, Y.	2012	Sparse F-IncSFA for action recognition [Abstract] [BibTeX] [URL]	Proc. of the 2012 JSME Conf. on Robotics and Mechatronics, Hamamatsu, Japan, May 27-29 .	inproceedings
Abstract: High dimensional input streams and unsupervised learning are two important factors in the area of humanoids and processes of the actions and movements of human. Our Fast Incremental Slow Feature Analysis (F-IncSFA) can learn and extract the few significant features of the complex sensory input sequences regarding high-level spatio-temporal conceptions. In this paper, the application of the F-IncSFA and some of its structure to make a hierarchical compound network made of F-IncSFA has been described. Also the techniques developed by adding efficient sparse coding as an encoder and a preprocessing step before an application of the F-IncSFA. The efficient sparse coding can dramatically reduces the dimension of extracted features and outcome of the efficient sparse coding are quite small as compared with the size of high-dimension video obtained by humanoid or human action. It has revealed excellent and promising dimension reduction by this preprocessor.
BibTeX: @inproceedings{LooBardia-2012, author = {Loo, Chukiong and Bardia, Yousefi}, title = {Sparse {F-IncSFA} for action recognition}, booktitle = {Proc.\ of the 2012 JSME Conf.\ on Robotics and Mechatronics, Hamamatsu, Japan, May 27-29}, year = {2012}, url = {http://eprints.um.edu.my/14089/1/1A1-P04.pdf} }
Loo, C. & Bardia, Y.	2012	1A1-P04 sparse F-IncSFA for action recognition (communication robot) [Abstract] [BibTeX]	ロボティクス・メカトロニクス講演会講演概要集 , 2012. Publ. 一般社団法人日本機械学会.	article
Abstract: High dimensional input streams and unsupervised learning are two important factors in the area of humanoids and processes of the actions and movements of human. Our Fast Incremental Slow Feature Analysis (F-IncSFA) can learn and extract the few significant features of the complex sensory input sequences regarding high-level spatio-temporal conceptions. In this paper, the application of the F-IncSFA and some of its structure to make a hierarchical compound network made of F-IncSFA has been described. Also the techniques developed by adding efficient sparse coding as an encoder and a preprocessing step before an application of the F-IncSFA. The efficient sparse coding can dramatically reduces the dimension of extracted features and outcome of the efficient sparse coding are quite small as compared with the size of high-dimension video obtained by humanoid or human action. It has revealed excellent and promising dimension reduction by this preprocessor.
BibTeX: @article{LooBardia-2012a, author = {Loo, Chukiong and Bardia, Yousefi}, title = {{1A1-P04} sparse {F-IncSFA} for action recognition (communication robot)}, journal = {ロボティクス・メカトロニクス講演会講演概要集}, publisher = {一般社団法人日本機械学会}, year = {2012}, volume = {2012} }
Luciw, M.; Kompella, V.; Kazerounian, S. & Schmidhuber, J.	2013	An intrinsic value system for developing multiple invariant representations with incremental slowness learning [Abstract] [BibTeX] [URL]	Front Neurorobot , 7, 9.	article
Abstract: Curiosity Driven Modular Incremental Slow Feature Analysis (CD-MISFA;) is a recently introduced model of intrinsically-motivated invariance learning. Artificial curiosity enables the orderly formation of multiple stable sensory representations to simplify the agent's complex sensory input. We discuss computational properties of the CD-MISFA model itself as well as neurophysiological analogs fulfilling similar functional roles. CD-MISFA combines 1. unsupervised representation learning through the slowness principle, 2. generation of an intrinsic reward signal through learning progress of the developing features, and 3. balancing of exploration and exploitation to maximize learning progress and quickly learn multiple feature sets for perceptual simplification. Experimental results on synthetic observations and on the iCub robot show that the intrinsic value system is essential for representation learning. Representations are typically explored and learned in order from least to most costly, as predicted by the theory of curiosity.
BibTeX: @article{LuciwKompellaEtAl-2013, author = {Luciw, M. and Kompella, V. and Kazerounian, S. and Schmidhuber, J.}, title = {An intrinsic value system for developing multiple invariant representations with incremental slowness learning}, journal = {Front Neurorobot}, year = {2013}, volume = {7}, pages = {9}, url = {http://journal.frontiersin.org/article/10.3389/fnbot.2013.00009/full}, doi = {http://doi.org/10.3389/fnbot.2013.00009} }
Luciw, M.; Kompella, V.R. & Schmidhuber, J.	2012	Hierarchical incremental slow feature analysis [Abstract] [BibTeX] [URL(2)]	Workshop on Deep Hierarchies in Vision (under CogSys2012) .	misc
Abstract: low feature analysis [1] (SFA) is an unsupervised learning technique that extracts features from an input stream with the objective of maintaining an informa- tive but slowly-changing feature response over time. Due to some promising results so far [1,2], SFA has an intriguing potential for autonomous agents that learn upon raw visual streams, but in order to realize this potential it needs to be both hierarchical and adaptive. An incremental version of Slow Feature Analysis, called IncSFA, was recently introduced [2,3,4]. Here, we focus on its hierarchical extension (H-IncSFA). H-IncSFA networks are composed of multiple layers of overlapping IncSFA units, where each unit has a local receptive field. Figure 1 shows an example H-IncSFA network, based on the one specified by Franzius et al. [5].
BibTeX: @misc{LuciwKompellaEtAl-2012, author = {Matthew Luciw and Varun Raj Kompella and J{\"u}rgen Schmidhuber}, title = {Hierarchical incremental slow feature analysis}, year = {2012}, howpublished = {Workshop on Deep Hierarchies in Vision (under CogSys2012)}, url2 = {http://www.idsia.ch/~luciw/papers/dhv12-luciw.pdf} }
Luciw, M. & Schmidhuber, J.	2012	Low complexity proto-value function learning from sensory observations with incremental slow feature analysis [Abstract] [BibTeX] [URL]	Artificial Neural Networks and Machine Learning - ICANN 2012 , Lecture Notes in Computer Science , 7553, 279-287. Eds. Villa, A.; Duch, W.; odzisł aw; É rdi, P.; ter; Masulli, F.; Palm, G. & nther Publ. Springer Berlin Heidelberg.	inproceedings
Abstract: We show that Incremental Slow Feature Analysis (IncSFA) provides a low complexity method for learning Proto-Value Functions (PVFs). It has been shown that a small number of PVFs provide a good basis set for linear approximation of value functions in reinforcement environments. Our method learns PVFs from a high-dimensional sensory input stream, as the agent explores its world, without building a transition model, adjacency matrix, or covariance matrix. A temporal-difference based reinforcement learner improves a value function approximation upon the features, and the agent uses the value function to achieve rewards successfully. The algorithm is local in space and time, furthering the biological plausibility and applicability of PVFs.
BibTeX: @inproceedings{LuciwSchmidhuber-2012, author = {Luciw, Matthew and Schmidhuber, J{\"u}rgen}, title = {Low complexity proto-value function learning from sensory observations with incremental slow feature analysis}, booktitle = {Artificial Neural Networks and Machine Learning -- ICANN 2012}, publisher = {Springer Berlin Heidelberg}, year = {2012}, volume = {7553}, pages = {279--287}, url = {http://link.springer.com/chapter/10.1007/978-3-642-33266-1_35}, doi = {http://doi.org/10.1007/978-3-642-33266-1_35} }
Ma, K.; Tao, Q. & Wang, J.	2010	Nonlinear blind source separation using slow feature analysis with random features [Abstract] [BibTeX] [URL]	20^th International Conference on Pattern Recognition (ICPR) , 830-833. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: We develop an algorithm RSFA to perform nonlinear blind source separation with temporal constraints. The algorithm is based on slow feature analysis using random Fourier features for shift invariant kernels, followed by a selection procedure to obtain the sought-after signals. This method not only obtains remarkable results in a short computing time, but also excellently handles situations where there are multiple types of mixtures. In kernel methods, since the problem is unsupervised, the need of multiple kernels is ubiquitous. Experiments on music excerpts illustrate the strong performance of our method.
BibTeX: @inproceedings{MaTaoEtAl-2010, author = {Kuijun Ma and Qing Tao and Jue Wang}, title = {Nonlinear blind source separation using slow feature analysis with random features}, booktitle = {20\textsuperscript{th} International Conference on Pattern Recognition (ICPR)}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2010}, pages = {830--833}, url = {http://ieeexplore.ieee.org/document/5596057/}, doi = {http://doi.org/10.1109/ICPR.2010.209} }
Ma, X.; Si, Y.; Yuan, Z.; Qin, Y. & Wang, Y.	2020	Multistep Dynamic Slow Feature Analysis for Industrial Process Monitoring [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Instrumentation and Measurement , 69(12), 9535-9548.	article
Abstract: Multivariate statistical process monitoring has been widely used in industry. However, traditional algorithms often ignore the dynamic characteristics of actual industry process. This study proposes a novel algorithm called multistep dynamic slow feature analysis (MS-DSFA), which has completed the full-condition monitoring of a dynamic system and divided dynamic structures more precisely. This algorithm achieves an optimal detection rate according to multiple control limits. To enrich the experiments, we select a numerical example, Tennessee Eastman process, and XJTU-SY bearing data sets to verify the universality of the algorithm. According to the overall score for optimal detection rates and false alarm rates, MS-DSFA stands out in the comparison of existing algorithms.
BibTeX: @article{9123944, author = {Ma, Xin and Si, Yabin and Yuan, Zeyi and Qin, Yihao and Wang, Youqing}, title = {Multistep Dynamic Slow Feature Analysis for Industrial Process Monitoring}, journal = {IEEE Transactions on Instrumentation and Measurement}, year = {2020}, volume = {69}, number = {12}, pages = {9535-9548}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=9123944}, url2 = {https://www.researchgate.net/publication/342430038_Multistep_Dynamic_Slow_Feature_Analysis_for_Industrial_Process_Monitoring}, doi = {http://doi.org/10.1109/TIM.2020.3004681} }
Malik, Z.K.; Hussain, A. & Wu, J.	2014	Novel biologically inspired approaches to extracting online information from temporal data [Abstract] [BibTeX] [URL]	Cognitive Computation , 6(3), 595-607. Publ. Springer.	article
Abstract: In this paper, we aim to develop novel learning approaches for extracting invariant features from time series. Specifically, we implement an existing method of solving the generalized eigenproblem and use this to firstly implement the biologically inspired technique of slow feature analysis (SFA) originally developed by Wiskott and Sejnowski (Neural Comput 14:715–770, 2002) and a rival method derived earlier by Stone (Neural Comput 8(7):1463–1492, 1996). Secondly, we investigate preprocessing the data using echo state networks (ESNs) (Lukosevicius and Jaeger in Comput Sci Rev 3(3):127–149, 2009) and show that the combination of generalized eigensolver and ESN is very powerful as a more biologically plausible implementation of SFA. Thirdly, we also investigate the effect of higher-order derivatives as a smoothing constraint and show the overall smoothness in the output signal. We demonstrate the potential of our proposed techniques, benchmarked against state-of-the-art approaches, using datasets comprising artificial, MNIST digits and hand-written character trajectories.
BibTeX: @article{MalikHussainEtAl-2014, author = {Malik, Zeeshan Khawar and Hussain, Amir and Wu, Jonathan}, title = {Novel biologically inspired approaches to extracting online information from temporal data}, journal = {Cognitive Computation}, publisher = {Springer}, year = {2014}, volume = {6}, number = {3}, pages = {595--607}, url = {http://link.springer.com/article/10.1007/s12559-014-9257-0}, doi = {http://doi.org/10.1007/s12559-014-9257-0} }
Marcos, M.I.C.	2010	Learning sensorimotor abstractions [Abstract] [BibTeX] [URL]	Aalto University, School of Science and Technology, Faculty of Information and Natural Sciences, Aalto University, School of Science and Technology, Faculty of Information and Natural Sciences . Publ. Universitat Politècnica de Catalunya.	phdthesis
Abstract: In order to interact with real environments, performing daily tasks, autonomous agents (as machines or robots) cannot be hard-coded. Given all the possible scenarios and, in each scenario, all the possible variations, it is impossible to take into account every single situation that the autonomous agent may encounter. Humans are able to interact with the changing world using as a guidance the sensory input perceived. Thus, autonomous agents need to be able to adapt to a changing environment. This work proposes a biologically inspired solution that allows the agent to learn representations and skills autonomously that prepare the agent for future learning tasks. The biologically inspired solution proposed here, called a cognitive architecture, follows the hierarchical architecture found in the cerebral cortex. This model permits the autonomous agent to extract useful information from the sensory input data it receives. The information is coded in abstractions, which are invariant features found within the input patterns. The cognitive architecture uses slowness as a principle for extracting features. In principle, unsupervised learning algorithms based on slowness try to find relevant and slowly changing data. This information could be useful for self evaluation. The agent tries to learn how to manipulate the sensory abstractions, by linking those to the motor ones. This allows the robot to find the mapping between the motor actions it is taking and the changes it is able to produce in the surrounding environment. Using the cognitive architecture, an example will be implemented. An agent, whoknows nothing about the environment it is placed on, will be able to learn how to move towards different places in space in an efficient (not random) way. Starting from random movements and capturing the sensory input data, it is able to learn concepts such as place and distance, which permits it to learn how to move towards a target efficiently
BibTeX: @phdthesis{Marcos-2010, author = {Mar{\'{i}}a Isabel Cordero Marcos}, title = {Learning sensorimotor abstractions}, publisher = {Universitat Polit{\`e}cnica de Catalunya}, school = {Aalto University, School of Science and Technology, Faculty of Information and Natural Sciences}, year = {2010}, url = {https://upcommons.upc.edu/bitstream/handle/2099.1/11435/62152.pdf} }
Maurer, A.	2006	Unsupervised slow subspace-learning from stationary processes [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Algorithmic Learning Theory , 363-377.	inproceedings
Abstract: We propose a method of unsupervised learning from stationary, vector-valued processes. A low-dimensional subspace is selected on the basis of a criterion which rewards data-variance (like PSA) and penalizes the variance of the velocity vector, thus exploiting the short-time dependencies of the process. We prove error bounds in terms of the β-mixing coefficients and consistency for absolutely regular processes. Experiments with image recognition demonstrate the algorithms ability to learn geometrically invariant feature maps
BibTeX: @inproceedings{Maurer-2006, author = {Maurer, Andreas}, title = {Unsupervised slow subspace-learning from stationary processes}, booktitle = {International Conference on Algorithmic Learning Theory}, year = {2006}, pages = {363--377}, url = {http://link.springer.com/chapter/10.1007/11894841_29}, url2 = {https://pdfs.semanticscholar.org/f761/c2bf0e993ec340d7b42c2e489ddab818553d.pdf}, doi = {http://doi.org/10.1007/11894841_29} }
Maurer, A.	2008	Unsupervised slow subspace-learning from stationary processes [Abstract] [BibTeX] [URL]	Theoretical Computer Science , 405(3), 237-255.	article
Abstract: We propose a method of unsupervised learning from stationary, vector-valued processes. A projection to a low-dimensional subspace is selected on the basis of an objective function which rewards data-variance and penalizes the variance of the velocity vector, thus exploiting the short-time dependencies of the process. We prove bounds on the estimation error of the objective in terms of the β-mixing coefficients of the process. It is also shown that maximizing the objective minimizes an error bound for simple classification algorithms on a generic class of learning tasks. Experiments with image recognition demonstrate the algorithms ability to learn geometrically invariant feature maps.
BibTeX: @article{Maurer-2008, author = {Andreas Maurer}, title = {Unsupervised slow subspace-learning from stationary processes}, journal = {Theoretical Computer Science}, year = {2008}, volume = {405}, number = {3}, pages = {237--255}, url = {http://www.sciencedirect.com/science/article/pii/S0304397508004593}, doi = {http://doi.org/10.1016/j.tcs.2008.06.054} }
Metka, B.; Franzius, M. & Bauer-Wersing, U.	2013	Outdoor self-localization of a mobile robot using slow feature analysis [Abstract] [BibTeX] [URL]	Neural Information Processing , Lecture Notes in Computer Science , 8226, 249-256. Eds. Lee, M.; Hirose, A.; Hou, Z.-G. & Kil, R. Publ. Springer Berlin Heidelberg.	incollection
Abstract: We apply slow feature analysis (SFA) to the problem of self-localization with a mobile robot. A similar unsupervised hierarchical model has earlier been shown to extract a virtual rat’s position as slowly varying features by directly processing the raw, high dimensional views captured during a training run. The learned representations encode the robot’s position, are orientation invariant and similar to cells in a rodent’s hippocampus. Here, we apply the model to virtual reality data and, for the first time, to data captured by a mobile outdoor robot. We extend the model by using an omnidirectional mirror, which allows to change the perceived image statistics for improved orientation invariance. The resulting representations are used for the notoriously difficult task of outdoor localization with mean absolute localization errors below 6%.
BibTeX: @incollection{MetkaFranziusEtAl-2013, author = {Metka, Benjamin and Franzius, Mathias and Bauer-Wersing, Ute}, title = {Outdoor self-localization of a mobile robot using slow feature analysis}, booktitle = {Neural Information Processing}, publisher = {Springer Berlin Heidelberg}, year = {2013}, volume = {8226}, pages = {249--256}, url = {http://link.springer.com/chapter/10.1007/978-3-642-42054-2_32}, doi = {http://doi.org/10.1007/978-3-642-42054-2_32} }
Metka, B.; Franzius, M. & Bauer-Wersing, U.	2016	Improving robustness of slow feature analysis based localization using loop closure events [Abstract] [BibTeX] [URL]	International Conference on Artificial Neural Networks , 489-496. Publ. Springer Nature.	inproceedings
Abstract: Hierarchical Slow Feature Analysis (SFA) extracts a spatial representation of the environment by directly processing images from a training run and has been shown to enable self-localization of a mobile robot by encoding its position as slowly varying features. However, in real world outdoor scenarios other variables, like global illumination or location of dynamic objects, might vary on an equal or slower time scale than the position of the robot. To prevent encoding of said variables we propose to restructure the temporal order of training samples based on loop closures in the trajectory. Every time the robot passes by a previously visited place, former recorded images are re-inserted to increase temporal variation of environmental variables. Hence, it is a feedback signal enforcing the model to produce similar outputs due to its slowness objective. Experiments in a simulated outdoor environment demonstrate increased robustness especially for changing lighting conditions.
BibTeX: @inproceedings{MetkaFranziusEtAl-2016, author = {Metka, Benjamin and Franzius, Mathias and Bauer-Wersing, Ute}, title = {Improving robustness of slow feature analysis based localization using loop closure events}, booktitle = {International Conference on Artificial Neural Networks}, publisher = {Springer Nature}, year = {2016}, pages = {489--496}, url = {http://link.springer.com/chapter/10.1007/978-3-319-44781-0_58}, doi = {http://doi.org/10.1007/978-3-319-44781-0_58} }
Metka, B.; Franzius, M. & Bauer-Wersing, U.	2017	Efficient navigation using slow feature gradients [BibTeX]	2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 1311-1316.	article
BibTeX: @article{MetkaFranziusEtAl-2017, author = {Benjamin Metka and Mathias Franzius and Ute Bauer-Wersing}, title = {Efficient navigation using slow feature gradients}, journal = {2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = {2017}, pages = {1311-1316}, doi = {http://doi.org/10.1109/iros.2017.8202307} }
Metka, B.; Franzius, M. & Bauer-Wersing, U.	2018	Bio-inspired visual self-localization in real world scenarios using Slow Feature Analysis [Abstract] [BibTeX] [URL]	PLOS ONE , 13(9), 1-18. Publ. Public Library of Science.	article
Abstract: We present a biologically motivated model for visual self-localization which extracts a spatial representation of the environment directly from high dimensional image data by employing a single unsupervised learning rule. The resulting representation encodes the position of the camera as slowly varying features while being invariant to its orientation resembling place cells in a rodent’s hippocampus. Using an omnidirectional mirror allows to manipulate the image statistics by adding simulated rotational movement for improved orientation invariance. We apply the model in indoor and outdoor experiments and, for the first time, compare its performance against two state of the art visual SLAM methods. Results of the experiments show that the proposed straightforward model enables a precise self-localization with accuracies in the range of 13-33cm demonstrating its competitiveness to the established SLAM methods in the tested scenarios.
BibTeX: @article{10.1371/journal.pone.0203994, author = {Metka, Benjamin AND Franzius, Mathias AND Bauer-Wersing, Ute}, title = {Bio-inspired visual self-localization in real world scenarios using Slow Feature Analysis}, journal = {PLOS ONE}, publisher = {Public Library of Science}, year = {2018}, volume = {13}, number = {9}, pages = {1-18}, url = {https://doi.org/10.1371/journal.pone.0203994}, doi = {http://doi.org/10.1371/journal.pone.0203994} }
Miao, J.; Xu, X.; Qiu, S.; Qing, C. & Tao, D.	2015	Temporal variance analysis for action recognition [Abstract] [BibTeX] [URL]	IEEE Transactions on Image Processing , 24(12), 5904-5915.	article
Abstract: Slow feature analysis (SFA) extracts slowly varying signals from input data and has been used to model complex cells in the primary visual cortex (V1). It transmits information to both ventral and dorsal pathways to process appearance and motion information respectively. However, SFA only uses slowly varying features for local feature extraction, because they represent appearance information more effectively than motion information. To better utilize temporal information, we propose temporal variance analysis (TVA) as a generalization of SFA. TVA learns a linear transformation matrix which projects multi-dimensional temporal data to temporal components with temporal variance. Inspired by the function of V1, we learn receptive fields by TVA and apply convolution and pooling to extract local features. Embedded in the improved dense trajectory framework, TVA for action recognition is proposed to: 1) extract appearance and motion features from gray using slow and fast filters respectively; 2) extract additional motion features using slow filters from horizontal and vertical optical flows; and 3) separately encode extracted local features with different temporal variances and concatenate all the encoded features as final features. We evaluate the proposed TVA features on several challenging datasets and show that both slow and fast features are useful in low level feature extraction. Experimental results show that the proposed TVA features outperform conventional histogram-based features, and excellent results can be achieved by combining all TVA features.
BibTeX: @article{MiaoXuEtAl-2015, author = {Miao, J. and Xu, X. and Qiu, S. and Qing, C. and Tao, D.}, title = {Temporal variance analysis for action recognition}, journal = {IEEE Transactions on Image Processing}, year = {2015}, volume = {24}, number = {12}, pages = {5904--5915}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7298412}, doi = {http://doi.org/10.1109/tip.2015.2490551} }
Miao, J.; Xu, X.; Xing, X. & Tao, D.	2017	Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition [Abstract] [BibTeX] [URL]	.	misc
Abstract: Dynamic textures exist in various forms, e.g., fire, smoke, and traffic jams, but recognizing dynamic texture is challenging due to the complex temporal variations. In this paper, we present a novel approach stemmed from slow feature analysis (SFA) for dynamic texture recognition. SFA extracts slowly varying features from fast varying signals. Fortunately, SFA is capable to leach invariant representations from dynamic textures. However, complex temporal variations require high-level semantic representations to fully achieve temporal slowness, and thus it is impractical to learn a high-level representation from dynamic textures directly by SFA. In order to learn a robust low-level feature to resolve the complexity of dynamic textures, we propose manifold regularized SFA (MR-SFA) by exploring the neighbor relationship of the initial state of each temporal transition and retaining the locality of their variations. Therefore, the learned features are not only slowly varying, but also partly predictable. MR-SFA for dynamic texture recognition is proposed in the following steps: 1) learning feature extraction functions as convolution filters by MR-SFA, 2) extracting local features by convolution and pooling, and 3) employing Fisher vectors to form a video-level representation for classification. Experimental results on dynamic texture and dynamic scene recognition datasets validate the effectiveness of the proposed approach.
BibTeX: @misc{miao2017manifold, author = {Jie Miao and Xiangmin Xu and Xiaofen Xing and Dacheng Tao}, title = {Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition}, year = {2017}, url = {https://arxiv.org/pdf/1706.03015.pdf} }
Miao, J.; Xu, X.; Xing, X. & Tao, D.	2017	Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition [BibTeX]	CoRR , abs/1706.03015.	article
BibTeX: @article{MiaoXuEtAl-2017, author = {Jie Miao and Xiangmin Xu and Xiaofen Xing and Dacheng Tao}, title = {Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition}, journal = {CoRR}, year = {2017}, volume = {abs/1706.03015} }
Miao, J.; Xu, X.; Xing, X. & Tao, D.	2017	Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition [BibTeX]	arXiv preprint arXiv:1706.03015 .	article
BibTeX: @article{MiaoXuEtAl-2017a, author = {Miao, Jie and Xu, Xiangmin and Xing, Xiaofen and Tao, Dacheng}, title = {Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition}, journal = {arXiv preprint arXiv:1706.03015}, year = {2017} }
Mikhailova, I.	2013	Energy-based state-feedback control of systems with mechanical or virtual springs [Abstract] [BibTeX] [URL]	2013 IEEE International Conference on Robotics and Automation (ICRA) , 2509-14. Publ. IEEE, Piscataway, NJ, USA.	inproceedings
Abstract: In the last years the classical optimal control of rigid structures gives way to alternatives both in hardware (elastic structures) as in software (non-linear control). In this work we consider both alternatives together. We test the possibility to apply speed-gradient (SG) control [1] to elastic structures. The SG method has many advantages, e.g. exploitation of natural dynamics of the system and mathematically provable criteria of goal achievement. However the cost function that satisfies the requirements of the SG method may be difficult to find. In this work we propose two approaches to this problem: usage of virtual springs and usage of learning methods based on Slow Feature Analysis (SFA). A classical example of a cart-pole system and an example of a system which uses two serial springs for hopping show in simulation the viability of our approach. Proposed here combination of SG control with learning is a novel approach which opens interesting perspectives for further research on passive control.
BibTeX: @inproceedings{Mikhailova-2013, author = {Mikhailova, I.}, title = {Energy-based state-feedback control of systems with mechanical or virtual springs}, booktitle = {2013 IEEE International Conference on Robotics and Automation (ICRA)}, publisher = {IEEE}, year = {2013}, pages = {2509--14}, url = {http://ieeexplore.ieee.org/document/6630919/}, doi = {http://doi.org/10.1109/ICRA.2013.6630919} }
Minh, H.Q. & Wiskott, L.	2013	Multivariate slow feature analysis and decorrelation filtering for blind source separation [Abstract] [BibTeX] [URL]	IEEE Trans Image Process , 22(7), 2737-2750.	article
Abstract: We generalize the method of Slow Feature Analysis (SFA) for vector-valued functions of several variables and apply it to the problem of blind source separation, in particular to image separation. It is generally necessary to use multivariate SFA instead of univariate SFA for separating multi-dimensional signals. For the linear case, an exact mathematical analysis is given, which shows in particular that the sources are perfectly separated by SFA if and only if they and their first-order derivatives are uncorrelated. When the sources are correlated, we apply the following technique called Decorrelation Filtering: use a linear filter to decorrelate the sources and their derivatives in the given mixture, then apply the unmixing matrix obtained on the filtered mixtures to the original mixtures. If the filtered sources are perfectly separated by this matrix, so are the original sources. A decorrelation filter can be numerically obtained by solving a nonlinear optimization problem. This technique can also be applied to other linear separation methods, whose output signals are decorrelated, such as ICA. When there are more mixtures than sources, one can determine the actual number of sources by using a regularized version of SFA with decorrelation filtering. Extensive numerical experiments using SFA and ICA with decorrelation filtering, supported by mathematical analysis, demonstrate the potential of our methods for solving problems involving blind source separation.
BibTeX: @article{MinhWiskott-2013, author = {Minh, H. Q. and Wiskott, L.}, title = {Multivariate slow feature analysis and decorrelation filtering for blind source separation}, journal = {IEEE Trans Image Process}, year = {2013}, volume = {22}, number = {7}, pages = {2737--2750}, url = {http://ieeexplore.ieee.org/document/6497610/}, doi = {http://doi.org/10.1109/TIP.2013.2257808} }
Mohmmed, U.S. & Saber, H.	2009	Blind separation of nonlinear mixing signals using kernel with slow feature analysis [Abstract] [BibTeX] [URL]	International Journal of Video & Image Processing and Network Security (IJVIPNS)International Journal of Video and Image Processing and Network Security IJVIPNS , 9(10).	article
Abstract: This paper describes a hybrid blind source separation approach (HBSSA) for nonlinear mixing model (NL-BSS). The proposed hybrid scheme combines simply the kernel-feature spaces separation technique (KTDSEP) and the principle of the slow feature analysis (SFA). The nonlinear mixed data is mapped to high dimensional feature space using kernel-based method. Then, the linear blind source separation (BSS) based on the slow feature analysis (SFA) is used to extract the most slowness vectors among the independent data vectors. The proposed scheme is based on the following four key features: 1) estimating an orthonormal bases, 2) mapping the data into the subspace using this orthonormal bases, 3) applying linear BSS on the mapping data to make the data vectors in the feature spaces are independent, 4) Applying the principle of slow feature analysis on the mapping data to select the desired signals. The SFA provides the dimension reduction according to the most independent and slowing variable signals. Moreover, the orthonormal bases estimation in the wavelet domain is introduced in this work to reduce the complexity of the KTDSEP algorithm. The motivation of using the wavelet transform, in estimating the orthonormal bases, is based on the fact that the low frequency band in the wavelet domain contains the significant power of the signal. The advantages of the proposed method are the fast estimation of the orthonormal bases and the dimension reduction of the estimating data vectors. Performed computer simulations have shown the effectiveness of the idea, even in presence of strong nonlinearities and synthetic mixture of real world data. Our extensive experiments have confirmed that the proposed procedure provides promising results.
BibTeX: @article{MohmmedSaber-2009, author = {Usama S. Mohmmed and Hany Saber}, title = {Blind separation of nonlinear mixing signals using kernel with slow feature analysis}, booktitle = {International Journal of Video and Image Processing and Network Security IJVIPNS}, journal = {International Journal of Video \& Image Processing and Network Security (IJVIPNS)}, year = {2009}, volume = {9}, number = {10}, url = {http://www.ijens.org/96310-7676%20IJVIPNS-IJENS.pdf} }
Müller, M.G.	2016	Slow Feature Analysis with Neural Networks [BibTeX]	mathesis, Information and Computer Engineering, TU Graz, Information and Computer Engineering, TU Graz .	mastersthesis
BibTeX: @mastersthesis{Mueller-2016, author = {Michael G. Müller}, title = {Slow Feature Analysis with Neural Networks}, school = {Information and Computer Engineering, TU Graz}, year = {2016} }
Nater, F.; Grabner, H. & Van Gool, L.	2011	Unsupervised workflow discovery in industrial environments [Abstract] [BibTeX] [URL] [URL(2)]	2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) , 1912-1919. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: In this work, we present an approach for the automatic discovery of workflows in industrial environments. In such cluttered scenes, one faces many challenges, which limit the use of state-of-the-art object detection and tracking meth- ods. Instead we propose a purely data-driven method which exploits the temporal structure of the workflow. Our robust technique is free of human intervention and does not need parameter tuning. We show results on two camera views of a working cell in a car assembly line. Workflows are extracted robustly, they match well across the camera views and they are conform with human annotation. Furthermore, we show a simple but efficient extension to analyze the im- age stream in real time. This assures a smooth running of the workflow and enables the notification of different types of unexpected scenarios.
BibTeX: @inproceedings{NaterGrabnerEtAl-2011a, author = {Nater, Fabian and Grabner, Helmut and Van Gool, Luc}, title = {Unsupervised workflow discovery in industrial environments}, booktitle = {2011 {IEEE} International Conference on Computer Vision Workshops ({ICCV} Workshops)}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2011}, pages = {1912--1919}, url = {http://ieeexplore.ieee.org/document/6130482/}, url2 = {https://pdfs.semanticscholar.org/8f77/bf698e34535e6b589939ec018c26910c6be3.pdf}, doi = {http://doi.org/10.1109/iccvw.2011.6130482} }
Nater, F.; Grabner, H. & Van Gool, L.J.	2011	Temporal relations in videos for unsupervised activity analysis. [Abstract] [BibTeX] [URL] [URL(2)]	Procedings of the British Machine Vision Conference 2011 , 2, 8. Publ. British Machine Vision Association and Society for Pattern Recognition.	inproceedings
Abstract: Temporal consistency is a strong cue in continuous data streams and especially in videos. We exploit this concept and encode temporal relations between consecutive frames using discriminative slow feature analysis. Activities are automatically segmented and represented in a hierarchical coarse to fine structure. Simultaneously, they are mod- eled in a generative manner, in order to analyze unseen data. This analysis supports the detection of previously learned activities and of abnormal, novel patterns. Our technique is purely data-driven and feature-independent. Experiments validate the approach in sev- eral contexts, such as traffic flow analysis and the monitoring of human behavior. The results are competitive with the state-of-the-art in all cases.
BibTeX: @inproceedings{NaterGrabnerEtAl-2011, author = {Nater, Fabian and Grabner, Helmut and Van Gool, Luc J}, title = {Temporal relations in videos for unsupervised activity analysis.}, booktitle = {Procedings of the British Machine Vision Conference 2011}, publisher = {British Machine Vision Association and Society for Pattern Recognition}, year = {2011}, volume = {2}, pages = {8}, url = {http://www.bmva.org/bmvc/2011/proceedings/paper21/index.html}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.714.8738&rep=rep1&type=pdf}, doi = {http://doi.org/10.5244/c.25.21} }
Ngiam, J. & Baldassano, C.	2009	Studies in deep belief networks [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Deep networks are able to learn good representations of unlabelled data via a greedy layer-wise approach to training. One challenge arises in choosing the layer types to use, whether it is an autoencoder, restricted boltzmann machine, with and without sparsity regularization. The layer choice directly affects the type of representations learned. In this paper, we examine sparse autoencoders and characterize their behavior under different parameterizations. We also present preliminary results on quadratic layers with slowness.
BibTeX: @misc{NgiamBaldassano-2009, author = {Ngiam, Jiquan and Baldassano, Chris}, title = {Studies in deep belief networks}, year = {2009}, url2 = {http://cs229.stanford.edu/proj2009/NgiamBaldassano.pdf} }
Nickisch, H.	2006	Extraction of visual features from natural video data using slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	Technische Universität Berlin, Fakultät für Elektrotechnik und Informatik, Technische Universität Berlin, Fakultät für Elektrotechnik und Informatik .	mastersthesis
Abstract: Das Forschungsprojekt NeuRoBot hat das unüberwachte Erlernen einer neu- ronal inspirierten Steuerungsarchitektur zum Ziel, und zwar unter den Rand- bedingungen biologischer Plausibilität und der Benutzung einer Kamera als einzigen Sensor. Visuelle Merkmale, die ein angemessenes Abbild der Umgebung liefern, sind unerlässlich, um das Ziel kollisionsfreier Naviga- tion zu erreichen. Zeitliche Kohärenz ist ein neues Lernprinzip, das in der Lage ist, Er- kenntnisse aus der Biologie des Sehens zu reproduzieren. Es wird durch die Beobachtung motiviert, dass die “Sensoren” der Retina auf deutlich kür- zeren Zeitskalen variieren als eine abstrakte Beschreibung. Zeitliche Lang- samkeitsanalyse löst das Problem, indem sie zeitlich langsam veränderliche Signale aus schnell veränderlichen Eingabesignalen extrahiert. Eine Verall- gemeinerung auf Signale, die nichtlinear von den Eingaben abhängen, ist durch die Anwendung des Kernel-Tricks möglich. Das einzig benutzte Vor- wissen ist die zeitliche Glattheit der gewonnenen Signale. In der vorliegenden Diplomarbeit wird Langsamkeitsanalyse auf Bild- ausschnitte von Videos einer Roboterkamera und einer Simulationsumge- bung angewendet. Zuallererst werden mittels Parameterexploration und Kreuzvalidierung die langsamst möglichen Funktionen bestimmt. Anschlie- ßend werden die Merkmalsfunktionen analysiert und einige Ansatzpunkte für ihre Interpretation angegeben. Aufgrund der sehr großen Datensätze und der umfangreichen Berechnungen behandelt ein Großteil dieser Arbeit auch Aufwandsbetrachtungen und Fragen der effizienten Berechnung. Kantendetektoren in verschiedenen Phasen und mit hauptsächlich hori- zontaler Orientierung stellen die wichtigsten aus der Analyse hervorgehen- den Funktionen dar. Eine Anwendung auf konkrete Navigationsaufgaben des Roboters konnte bisher nicht erreicht werden. Eine visuelle Interpreta- tion der erlernten Merkmale ist jedoch durchaus gegeben.
BibTeX: @mastersthesis{Nickisch-2006, author = {Nickisch, Hannes}, title = {Extraction of visual features from natural video data using slow feature analysis}, school = {Technische Universit{\"{a}}t Berlin, Fakult{\"{a}}t f{\"{u}}r Elektrotechnik und Informatik}, year = {2006}, url = {http://www.kyb.mpg.de/fileadmin/user_upload/files/publications/thesis_4190[0].pdf}, url2 = {https://pdfs.semanticscholar.org/7cf4/4a7e2344b5b76e0debf90cdda37b98e7f2ff.pdf} }
Nicolaou, M.A.; Zafeiriou, S. & Pantic, M.	2014	A unified framework for probabilistic component analysis [Abstract] [BibTeX] [URL] [URL(2)]	Joint European Conference on Machine Learning and Knowledge Discovery in Databases , 469-484.	inproceedings
Abstract: We present a unifying framework which reduces the construction of probabilistic component analysis techniques to a mere selection of the latent neighbourhood, thus providing an elegant and principled framework for creating novel component analysis models as well as constructing probabilistic equivalents of deterministic component analysis methods. Under our framework, we unify many very popular and well-studied component analysis algorithms, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Locality Preserving Projections (LPP) and Slow Feature Analysis (SFA), some of which have no probabilistic equivalents in literature thus far. We firstly define the Markov Random Fields (MRFs) which encapsulate the latent connectivity of the aforementioned component analysis techniques; subsequently, we show that the projection directions produced by all PCA, LDA, LPP and SFA are also produced by the Maximum Likelihood (ML) solution of a single joint probability density function, composed by selecting one of the defined MRF priors while utilising a simple observation model. Furthermore, we propose novel Expectation Maximization (EM) algorithms, exploiting the proposed joint PDF, while we generalize the proposed methodologies to arbitrary connectivities via parametrizable MRF products. Theoretical analysis and experiments on both simulated and real world data show the usefulness of the proposed framework, by deriving methods which well outperform state-of-the-art equivalents.
BibTeX: @inproceedings{NicolaouZafeiriouEtAl-2014, author = {Nicolaou, Mihalis A and Zafeiriou, Stefanos and Pantic, Maja}, title = {A unified framework for probabilistic component analysis}, booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, year = {2014}, pages = {469--484}, url = {http://link.springer.com/chapter/10.1007/978-3-662-44851-9_30}, url2 = {https://pdfs.semanticscholar.org/73a5/54f9d2c96a7bb5455878a4361b6eda4ba683.pdf}, doi = {http://doi.org/10.1007/978-3-662-44851-9_30} }
Nishikawa, A.; Ogino, M. & Asada, M.	2011	Acquiring body representation for reinforcement learning based on slow feature analysis [Abstract] [BibTeX] [URL(2)]	The 21^st Annual Conference of the Japanese Neural Network Society , 3-29.	inproceedings
Abstract: The center of spatio-temporal represen- tation for own body and its surrounding space is sup- posed at the parietal cortex in human brains, but the mechanism how the brain computes them is still not clearly understood though its hierarchical represen- tation is expected. One of such hierarchical models, this paper propose a method which integrates multi- modal information based on the Slow Feature Analysis (SFA) that enables sensory data abstraction in one modality and integration of abstracted multi-modal sensory information. To verify the proposed method, the reinforcement learning of reaching behavior is ap- plied where the acquired representation from the visual and somatosensory information of arm movements of a robot is utilised as state space representation. The simulation result shows that multimodal information related to self movement is transformed into lower di- mensional data that changes slowly, which is useful for reinforcement learning to improve its performance.
BibTeX: @inproceedings{NishikawaOginoEtAl-2011, author = {Akihiko Nishikawa and Masaki Ogino and Minoru Asada}, title = {Acquiring body representation for reinforcement learning based on slow feature analysis}, booktitle = {The 21\textsuperscript{st} Annual Conference of the Japanese Neural Network Society}, year = {2011}, pages = {3--29}, url2 = {http://www.er.ams.eng.osaka-u.ac.jp/Paper/2011/Nishikawa11b.pdf} }
Ogino, M.; Nishikawa, A. & Asada, M.	2013	A motivation model for interaction between parent and child based on the need for relatedness [Abstract] [BibTeX] [URL]	Frontiers in Psychology , 4, 618.	article
Abstract: In communication between parents and children, various kinds of intrinsic and extrinsic motivations affect the emotions that encourage actions to promote more interactions. This paper presents a motivation model for the interaction between an infant and a caregiver which models relatedness, one of the most important basic psychological needs, as a variable that increases with experiences of emotion sharing. Relatedness is not only an important factor of pleasure but also a meta-factor which affects other factors such as stress and emotion mirroring. In the simulation experiment, two agents, each of which has the proposed motivation model, show emotional communication depending on the relatedness level that is similar to actual human communication. Especially, the proposed model can reproduce a finding described by the "still-face paradigm", in which an infant shows unpleasant emotion when a caregiver suddenly stops facial expressions. The proposed model is implemented in an artificial agent with a recognition system for gestures and facial expressions. The baby-like agent successfully interacts with an actual human and shows reactions comparable to the "still-face paradigm".
BibTeX: @article{OginoNishikawaEtAl-2013, author = {Ogino, Masaki and Nishikawa, Akihiko and Asada, Minoru}, title = {A motivation model for interaction between parent and child based on the need for relatedness}, journal = {Frontiers in Psychology}, year = {2013}, volume = {4}, pages = {618}, url = {http://journal.frontiersin.org/article/10.3389/fpsyg.2013.00618/full}, doi = {http://doi.org/10.3389/fpsyg.2013.00618} }
Omori, T.	2013	Extracting latent dynamics from multi-dimensional data by probabilistic slow feature analysis [Abstract] [BibTeX] [URL]	Neural Information Processing , Lecture Notes in Computer Science , 8228, 108-116. Eds. Lee, M.; Hirose, A.; Hou, Z.-G. & Kil, R. Publ. Springer Berlin Heidelberg.	incollection
Abstract: Slow feature analysis (SFA) is a time-series analysis method for extracting slowly-varying latent features from multi-dimensional data. In this paper, the probabilistic version of SFA algorithms is discussed from a theoretical point of view. First, the fundamental notions of SFA algorithms are reviewed in order to show the mechanism of extracting the slowly-varying latent features by means of the SFA. Second, recent advances in the SFA algorithms are described on the emphasis of the probabilistic version of the SFA. Third, the probabilistic SFA with rigorously derived likelihood function is derived by means of belief propagation. Using the rigorously derived likelihood function, we simultaneously extracts slow features and underlying parameters for the latent dynamics. Finally, we show using synthetic data that the probabilistic SFA with rigorously derived likelihood function can estimate the slow feature accurately even under noisy environments.
BibTeX: @incollection{Omori-2013, author = {Omori, Toshiaki}, title = {Extracting latent dynamics from multi-dimensional data by probabilistic slow feature analysis}, booktitle = {Neural Information Processing}, publisher = {Springer Berlin Heidelberg}, year = {2013}, volume = {8228}, pages = {108--116}, url = {http://link.springer.com/chapter/10.1007/978-3-642-42051-1_15}, doi = {http://doi.org/10.1007/978-3-642-42051-1_15} }
Omori, T.; Sekiguchi, T. & Okada, M.	2017	Belief Propagation for Probabilistic Slow Feature Analysis [BibTeX]	Journal of the Physical Society of Japan , 86(8), 084802. Publ. The Physical Society of Japan.	article
BibTeX: @article{OmoriSekiguchiEtAl-2017, author = {Omori, Toshiaki and Sekiguchi, Tomoki and Okada, Masato}, title = {Belief Propagation for Probabilistic Slow Feature Analysis}, journal = {Journal of the Physical Society of Japan}, publisher = {The Physical Society of Japan}, year = {2017}, volume = {86}, number = {8}, pages = {084802}, doi = {http://doi.org/10.7566/jpsj.86.084802} }
Pagel, F.	2015	Unsupervised classification and visual representation of situations in surveillance videos using slow feature analysis for situation retrieval applications [Abstract] [BibTeX] [URL]	SPIE/IS&T Electronic Imaging , 94070H-94070H.	inproceedings
Abstract: Today, video surveillance systems produce thousands of terabytes of data. This source of information can be very valuable, as it contains spatio-temporal information about abnormal, similar or periodic activities. However, a search for certain situations or activities in unstructured large-scale video footage can be exhausting or even pointless. Searching surveillance video footage is extremely difficult due to the apparent similarity of situations, especially for human observers. In order to keep this amount manageable and hence usable, this paper aims at clustering situations regarding their visual content as well as motion patterns. Besides standard image content descriptors like HOG, we present and investigate novel descriptors, called Franklets, which explicitly encode motion patterns for certain image regions. Slow feature analysis (SFA) will be performed for dimension reduction based on the temporal variance of the features. By reducing the dimension with SFA, a higher feature discrimination can be reached compared to standard PCA dimension reduction. The effects of dimension reduction via SFA will be investigated in this paper. Cluster results on real data from the Hamburg Harbour Anniversary 2014 will be presented with both, HOG feature descriptors and Franklets. Furthermore, we could show that by using SFA an improvement to standard PCA techniques could be achieved. Finally, an application to visual clustering with self-organizing maps will be introduced.
BibTeX: @inproceedings{Pagel-2015, author = {Pagel, Frank}, title = {Unsupervised classification and visual representation of situations in surveillance videos using slow feature analysis for situation retrieval applications}, booktitle = {SPIE/IS\&T Electronic Imaging}, year = {2015}, pages = {94070H--94070H}, url = {http://akme-a2.iosb.fraunhofer.de/EatThisGoogleScholar/d/2015_Unsupervised%20classification%20and%20visual%20representation%20of%20situations%20in%20surveillance%20videos%20using%20slow%20feature%20analysis%20for%20situation%20retrieval%20applica.pdf}, doi = {http://doi.org/10.1117/12.2076740} }
Pan, X.; Wang, G. & Yang, P.	2018	Extracting the signal of driving force from hierarchical system by Slow Feature Analysis [BibTeX]	EGU General Assembly Conference Abstracts , 20, 3895.	inproceedings
BibTeX: @inproceedings{PanWangEtAl-2018, author = {Pan, Xinnong and Wang, Geli and Yang, Peicai}, title = {Extracting the signal of driving force from hierarchical system by Slow Feature Analysis}, booktitle = {EGU General Assembly Conference Abstracts}, year = {2018}, volume = {20}, pages = {3895} }
Pang, C.; Wang, M.; Liu, W. & Li, B.	2016	Learning features for discriminative behavior analysis of evolutionary algorithms via slow feature analysis [Abstract] [BibTeX] [URL]	Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion , 1437-1444. Publ. Association for Computing Machinery (ACM).	inproceedings
Abstract: Evolutionary algorithms (EAs) are a kind of stochastic optimization methods, which have been testified to be powerful in solving many real-world hard problems in past decades. But till now, we are still short of effective methods to represent and investigate their collective behaviors in various environments, which are very useful for researchers and engineers in Evolutionary Computation to understand the algorithms better. This paper is a preliminary effort to tackle above issue. We attempt to analyze the generation-wise collective behavior of EAs via an approach called feature learning. An unsupervised feature learning framework based on Slow Feature Analysis (SFA) is presented to extract discriminative features from the generation-wise collective behavior data of several EAs on various fitness landscapes, with the purpose of finding out whether there exist differences between the searching behavior of different EAs running on the same fitness landscape; and whether there are differences between the behavior of one algorithm running on different fitness landscapes. Besides, the relationship between the fitness landscape and the searching behavior of EA is also studied. In the experiments, several typical EAs and classical benchmark functions with typical landscapes are selected as the study subjects. The collective behaviors of various EAs are visualized and compared in the extracted feature space.
BibTeX: @inproceedings{PangWangEtAl-2016, author = {Pang, Chengshan and Wang, Mang and Liu, Weiming and Li, Bin}, title = {Learning features for discriminative behavior analysis of evolutionary algorithms via slow feature analysis}, booktitle = {Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion}, publisher = {Association for Computing Machinery ({ACM})}, year = {2016}, pages = {1437--1444}, url = {http://dl.acm.org/citation.cfm?doid=2908961.2935617}, doi = {http://doi.org/10.1145/2908961.2935617} }
Puli, V.K.; Raveendran, R. & Huang, B.	2021	Complex probabilistic slow feature extraction with applications in process data analytics [Abstract] [BibTeX] [URL]	Computers & Chemical Engineering , 154, 107456.	article
Abstract: Today, in modern industrial processes, thousands of correlated process variables are measured and stored. Dimension reduction techniques are often employed to construct informative features by discarding redundant information. Slow feature analysis is one such technique that extracts the slowly varying patterns from measured data. Oscillatory behaviour is prevalent in process data due to inadequate control loop tuning and external disturbances such as diurnal temperature variation. Extracting these oscillatory patterns is vital in applications such as control loop monitoring, fault diagnosis. Slow feature analysis may not extract oscillating patterns when the signal to noise ratio is low in process data. This paper proposes the complex probabilistic formulation that extracts slow oscillatory features. We also present the Expectation-Maximization algorithm to obtain the optimal parameter estimates. Finally, three case studies are presented to illustrate the efficacy of the proposed formulation in soft sensing and fault detection applications.
BibTeX: @article{PULI2021107456, author = {Vamsi Krishna Puli and Rahul Raveendran and Biao Huang}, title = {Complex probabilistic slow feature extraction with applications in process data analytics}, journal = {Computers & Chemical Engineering}, year = {2021}, volume = {154}, pages = {107456}, url = {https://www.sciencedirect.com/science/article/pii/S0098135421002349}, doi = {http://doi.org/10.1016/j.compchemeng.2021.107456} }
Qi, X.; Li, C.; Zhao, G.; Hong, X. & Pietikäinen, M.	2015	Dynamic texture and scene classification by transferring deep image features [Abstract] [BibTeX] [URL]	e-print arXiv:1502.00303 .	misc
Abstract: Dynamic texture and scene classification are two fundamental problems in understanding natural video content. Extracting robust and effective features is a crucial step towards solving these problems. However the existing approaches suffer from the sensitivity to either varying illumination, or viewpoint changing, or even camera motion, and/or the lack of spatial information. Inspired by the success of deep structures in image classification, we attempt to leverage a deep structure to extract feature for dynamic texture and scene classification. To tackle with the challenges in training a deep structure, we propose to transfer some prior knowledge from image domain to video domain. To be specific, we propose to apply a well-trained Convolutional Neural Network (ConvNet) as a mid-level feature extractor to extract features from each frame, and then form a representation of a video by concatenating the first and the second order statis- tics over the mid-level features. We term this two-level feature extraction scheme as a Transferred ConvNet Feature (TCoF). Moreover we explore two different implementations of the TCoF scheme, i.e., the spatial TCoF and the temporal TCoF, in which the mean-removed frames and the difference between two adjacent frames are used as the inputs of the ConvNet, respectively. We evaluate systematically the proposed spatial TCoF and the temporal TCoF schemes on three benchmark data sets, including DynTex, YUPENN, and Maryland, and demonstrate that the proposed approach yields superior performance.
BibTeX: @misc{QiLiEtAl-2015, author = {Xianbiao Qi and Chun{-}Guang Li and Guoying Zhao and Xiaopeng Hong and Matti Pietik{\"{a}}inen}, title = {Dynamic texture and scene classification by transferring deep image features}, year = {2015}, howpublished = {e-print arXiv:1502.00303}, url = {https://arxiv.org/pdf/1502.00303.pdf} }
Qi, X.; Li, C.-G.; Zhao, G.; Hong, X. & Pietikäinen, M.	2016	Dynamic texture and scene classification by transferring deep image features [Abstract] [BibTeX] [URL]	Neurocomputing , 171, 1230-1241. Publ. Elsevier.	article
Abstract: Dynamic texture and scene classification are two fundamental problems in understanding natural video content. Extracting robust and effective features is a crucial step towards solving these problems. However, the existing approaches suffer from the sensitivity to either varying illumination, or viewpoint changes, or even camera motion, and/or the lack of spatial information. Inspired by the success of deep structures in image classification, we attempt to leverage a deep structure to extract features for dynamic texture and scene classification. To tackle with the challenges in training a deep structure, we propose to transfer some prior knowledge from image domain to video domain. To be more specific, we propose to apply a well-trained Convolutional Neural Network (ConvNet) as a feature extractor to extract mid-level features from each frame, and then form the video-level representation by concatenating the first and the second order statistics over the mid-level features. We term this two-level feature extraction scheme as a Transferred ConvNet Feature (TCoF). Moreover, we explore two different implementations of the TCoF scheme, i.e., the spatial TCoF and the temporal TCoF. In the spatial TCoF, the mean-removed frames are used as the inputs of the ConvNet; whereas in the temporal TCoF, the differences between two adjacent frames are used as the inputs of the ConvNet. We evaluate systematically the proposed spatial TCoF and the temporal TCoF schemes on three benchmark data sets, including DynTex, YUPENN, and Maryland, and demonstrate that the proposed approach yields superior performance.
BibTeX: @article{QiLiEtAl-2016, author = {Qi, Xianbiao and Li, Chun-Guang and Zhao, Guoying and Hong, Xiaopeng and Pietik{\"a}inen, Matti}, title = {Dynamic texture and scene classification by transferring deep image features}, journal = {Neurocomputing}, publisher = {Elsevier}, year = {2016}, volume = {171}, pages = {1230--1241}, url = {http://www.sciencedirect.com/science/article/pii/S0925231215010784}, doi = {http://doi.org/10.1016/j.neucom.2015.07.071} }
Qian, H.; Zhou, J.; Lu, X. & Wu, X.	2014	Human activities recognition based on poisson equation evaluation and bidirectional 2DPCA [Abstract] [BibTeX] [URL]	Conference on Control Automation Robotics & Vision (ICARCV), 2014 13^th International , 787-792.	inproceedings
Abstract: A novel algorithm for the human activities recognition based on the Poisson images and via bidirectional two-dimensional principal component analysis (2DPCA) is presented in this note, where the Poisson images are defined by solving the Poisson equations to re-interpret the motion accumulation image (MAI). More precisely, firstly, object detection based on the Gaussian Mixture Model (GMM) is applied to acquire the binary images including moving human blobs; secondly, the Poisson image is defined to make the features extracted in the sequel robust to possible incomplete human blobs; thirdly, the principal component analysis (PCA), 2DPCA and bidirectional 2DPCA are applied, respectively, to extract the feature vectors; and finally, the nearest neighbour (NN) classifier is used to recognize the human activities. Simulation results on Weizmann database confirm the recognition performance of the proposed algorithm. Comparisons in terms of classification accuracy and time consumption in between the three methods show that the bidirectional 2DPCA is optimal.
BibTeX: @inproceedings{QianZhouEtAl-2014, author = {Qian, Huimin and Zhou, Jun and Lu, Xinbiao and Wu, Xinye}, title = {Human activities recognition based on poisson equation evaluation and bidirectional {2DPCA}}, booktitle = {Conference on Control Automation Robotics \& Vision (ICARCV), 2014 13\textsuperscript{th} International}, year = {2014}, pages = {787--792}, url = {http://ieeexplore.ieee.org/document/7064404/}, doi = {http://doi.org/10.1109/icarcv.2014.7064404} }
Qin, Y.; Li, W.-T.; Yuen, C.; Tushar, W. & Saha, T.	2021	IIoT-Enabled Health Monitoring for Integrated Heat Pump System Using Mixture Slow Feature Analysis [Abstract] [BibTeX] [URL]	IEEE Transactions on Industrial Informatics , 1-1.	article
Abstract: The sustaining evolution of sensing and advancement in communications technologies have revolutionized prognostics and health management for various electrical equipment towards data-driven ways. This revolution delivers a promising solution for the health monitoring problem of heat pump (HP) system to avoid unexpected downtime. Many HPs were practically manufactured and installed many years ago, resulting in fewer sensors available due to technology limitations and cost control at that time. We propose a hybrid scheme by integrating industrial Internet-of-Things (IIoT) and intelligent health monitoring algorithms to handle this challenge. An unsupervised learning algorithm named mixture slow feature analysis (MSFA) is proposed to timely evaluate the health status of the integrated HP only using water temperature. The experimental results on a real integrated HP show that MSFA is capable of accurately identifying health status of the system, especially failure at a preliminary stage compared to its competing algorithm.
BibTeX: @article{9416833, author = {Qin, Yan and Li, Wen-Tai and Yuen, Chau and Tushar, Wayes and Saha, Tapan}, title = {IIoT-Enabled Health Monitoring for Integrated Heat Pump System Using Mixture Slow Feature Analysis}, journal = {IEEE Transactions on Industrial Informatics}, year = {2021}, pages = {1-1}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9416833}, doi = {http://doi.org/10.1109/TII.2021.3075708} }
Qin, Y. & Zhao, C.	2019	Comprehensive process decomposition for closed-loop process monitoring with quality-relevant slow feature analysis [Abstract] [BibTeX] [URL]	Journal of Process Control , 77, 141-154.	article
Abstract: In modern industrial processes, quality-relevant process monitoring methods are important to timely indicate abnormal product quality. Moreover, advanced closed-loop control systems have been widely applied to ensure consistent product quality. The process variations under closed-loop systems are obviously different from that of open-loop systems. The dynamics caused by feedback control brings challenges for quality-relevant process monitoring issue which has rarely been addressed before. Considering slowness is a good indicator of dynamics, a comprehensive decomposition of process variation is proposed with dual consideration of product quality and slowness. First, quality-relevant process variations are separated from process-relevant variations by maximizing correlation between latent variables and product quality meanwhile minimizing the slowness of latent variables. Both variations are further divided into static and dynamic subspaces with respect to temporal information. Thus, total process variations are decomposed into three subspaces, in which each one has a specific meaning. On the basis of this, the proposed method possesses the ability in simultaneously evaluating the influences on product quality and process dynamics which thus provides a fine-scale monitoring of process status. Finally, the efficacy of the proposed method is illustrated through a benchmark case and an industrial process, which are both under closed-loop control.
BibTeX: @article{QIN2019141, author = {Yan Qin and Chunhui Zhao}, title = {Comprehensive process decomposition for closed-loop process monitoring with quality-relevant slow feature analysis}, journal = {Journal of Process Control}, year = {2019}, volume = {77}, pages = {141-154}, url = {https://www.sciencedirect.com/science/article/pii/S0959152418304505}, doi = {http://doi.org/10.1016/j.jprocont.2019.04.001} }
Rehn, E.M.	2013	On the slowness principle and learning in hierarchical temporal memory [Abstract] [BibTeX]	Bernstein Center for Computational Neuroscience, Bernstein Center for Computational Neuroscience . , Berlin, Germany	mastersthesis
Abstract: The slowness principle is believed to be one clue to how the brain solves the problem of invariant object recognition. It states that external causes for sensory activation, i.e., distal stimuli, often vary on a much slower time scale than the sensory activation itself. Slowness is thus a plausible objective when the brain learns invariant representations of its environment. Here we review two approaches to slowness learning: Slow Feature Analysis (SFA) and Hierarchical Temporal Memory (HTM), and show how Generalized SFA (GSFA) links the two. The connection between SFA, Linear Discriminant Analysis (LDA), and Locality Preserving Projections (LPP) is also investigated. Experimental work is presented which demonstrates how the local neighborhood implicit in the original SFA formulation, by the use of the temporal derivative of the input, renders SFA more efficient than LDA when applied to supervised pattern recognition, if the data has a low-dimensional manifold structure. Furthermore, a novel object recognition model, called Hierarchical Generalized Slow Feature Analysis (HGSFA), is proposed. Through the use of GSFA, the model enables a possible manifold structure in the training data to be exploited during training, and the experimental evaluation shows how this leads to greatly increased classification accuracy on the NORB object recognition dataset, compared to previously published results. Lastly, a novel gradient-based fine-tuning algorithm for HTM is proposed and evaluated. This error backpropagation can be naturally and elegantly implemented through native HTM belief propagation, and experimental results show that a two- stage training process composed by temporal unsupervised pre-training and supervised refinement is very effective. This is in line with recent findings on other deep architectures, where generative pre-training is complemented by discriminant fine-tuning.
BibTeX: @mastersthesis{Rehn-2013, author = {Erik M. Rehn}, title = {On the slowness principle and learning in hierarchical temporal memory}, school = {Bernstein Center for Computational Neuroscience}, year = {2013} }
Rehn, E.M. & Sprekeler, H.	2014	Nonlinear supervised locality preserving projections for visual pattern discrimination. [Abstract] [BibTeX] [URL] [URL(2)]	ICPR , 1568-1573.	inproceedings
Abstract: Learning representations that disentangle hidden explanatory factors in data has proven beneficial for effective pattern classification. Slow feature analysis (SFA) is a nonlinear dimensionality reduction technique that provides a useful representation for classification if the training data is sequential and transitions between classes are rare. The pattern discrimination ability of SFA has been attributed to the equivalence of linear SFA and linear discriminant analysis (LDA) under certain conditions. LDA, however, is often outperformed by locality preserving projections (LPP) when the data lies on or near a low-dimensional manifold. Here, we take a unified manifold learning perspective on LPP, LDA and SFA. We suggest that the discrimination ability of SFA is better explained by its relation to LPP than to LDA, and give an example of a situation where linear SFA outperforms LDA. We then propose a novel supervised manifold learning architecture that combines hierarchical nonlinear expansions, as commonly used for SFA, with supervised LPP. It learns a nonlinear parametric data representation that explicitly takes both the class labels and the manifold structure of the data into account. As an experimental validation, we show that this approach outperforms previously proposed models on the NORB object recognition dataset.
BibTeX: @inproceedings{RehnSprekeler-2014, author = {Rehn, Erik M and Sprekeler, Henning}, title = {Nonlinear supervised locality preserving projections for visual pattern discrimination.}, booktitle = {ICPR}, year = {2014}, pages = {1568--1573}, url = {http://ieeexplore.ieee.org/document/6976988/}, url2 = {https://pdfs.semanticscholar.org/9f06/75fc265f9902d7d0f1c9460c7cf7ebbd1542.pdf}, doi = {http://doi.org/10.1109/icpr.2014.278} }
Richthofer, S. & Wiskott, L.	2018	Global Navigation Using Predictable and Slow Feature Analysis in Multiroom Environments, Path Planning and Other Control Tasks [Abstract] [BibTeX] [URL]	.	misc
Abstract: Extended Predictable Feature Analysis (PFAx) [Richthofer and Wiskott, 2017] is an extension of PFA [Richthofer and Wiskott, 2015] that allows generating a goal-directed control signal of an agent whose dynamics has previously been learned during a training phase in an unsupervised manner. PFAx hardly requires assumptions or prior knowledge of the agent's sensor or control mechanics, or of the environment. It selects features from a high-dimensional input by intrinsic predictability and organizes them into a reasonably low-dimensional model. While PFA obtains a well predictable model, PFAx yields a model ideally suited for manipulations with predictable outcome. This allows for goal-directed manipulation of an agent and thus for local navigation, i.e. for reaching states where intermediate actions can be chosen by a permanent descent of distance to the goal. The approach is limited when it comes to global navigation, e.g. involving obstacles or multiple rooms. In this article, we extend theoretical results from [Sprekeler and Wiskott, 2008], enabling PFAx to perform stable global navigation. So far, the most widely exploited characteristic of Slow Feature Analysis (SFA) was that slowness yields invariances. We focus on another fundamental characteristics of slow signals: They tend to yield monotonicity and one significant property of monotonicity is that local optimization is sufficient to find a global optimum. We present an SFA-based algorithm that structures an environment such that navigation tasks hierarchically decompose into subgoals. Each of these can be efficiently achieved by PFAx, yielding an overall global solution of the task. The algorithm needs to explore and process an environment only once and can then perform all sorts of navigation tasks efficiently. We support this algorithm by mathematical theory and apply it to different problems.
BibTeX: @misc{richthofer2018global, author = {Stefan Richthofer and Laurenz Wiskott}, title = {Global Navigation Using Predictable and Slow Feature Analysis in Multiroom Environments, Path Planning and Other Control Tasks}, year = {2018}, url = {https://arxiv.org/abs/1805.08565} }
Richthofer, S. & Wiskott, L.	2018	Global Navigation Using Predictable and Slow Feature Analysis in Multiroom Environments, Path Planning and Other Control Tasks [BibTeX]	CoRR , abs/1805.08565.	article
BibTeX: @article{RichthoferWiskott-2018, author = {Stefan Richthofer and Laurenz Wiskott}, title = {Global Navigation Using Predictable and Slow Feature Analysis in Multiroom Environments, Path Planning and Other Control Tasks}, journal = {CoRR}, year = {2018}, volume = {abs/1805.08565} }
Rubia, L.B. & Manimala, K.	2013	Slow feature analysis for recognizing prisoner’s activities to assist jail authorities [Abstract] [BibTeX] [URL]	International Journal of Advances in Engineering and Emerging Technology (IJAEET) , 1(1).	article
Abstract: Slow Feature Analysis (SFA) has been established as a robust and versatile technique from the neurosciences to learn slowly varying functions from quick ly changing signals. SFA framework is introduced to the problem of recognizing prisoner’s actions by incorporating the supervised information with the original unsupervised SFA learning. Firstly, large amount of cuboids are collected in the motion boundaries, and local feature is described with SFA method. Each action sequence is represented by the Accumulated Squared Derivative (ASD), which is a statistical distribution of the slow features in an action sequence [1]. The descriptive statistical features are extracted inorder to reduce the dimension of the ASD feature is proposed. Finally, one against all support vector machine (SVM) is trained to classify action represented by statistical featur
BibTeX: @article{RubiaManimala-2013, author = {Rubia, L Berwin and Manimala, K}, title = {Slow feature analysis for recognizing prisoner{\textquoteright}s activities to assist jail authorities}, journal = {International Journal of Advances in Engineering and Emerging Technology (IJAEET)}, year = {2013}, volume = {1}, number = {1}, url = {http://erlibrary.org/papers/ijaeet/v1/i1/ERL-101227.pdf} }
Rubia, L.B. & Manimala, K.	2017	Slow Feature Analysis for Recognizing Prisoner ’ s Activities to Assist Jail Authorities [BibTeX]	.	inproceedings
BibTeX: @inproceedings{RubiaManimala-2017, author = {L. Berwin Rubia and K. Manimala}, title = {Slow Feature Analysis for Recognizing Prisoner ’ s Activities to Assist Jail Authorities}, year = {2017} }
Saafan, H. & Zhu, Q.	2021	Comprehensive Monitoring with Incremental Slow Feature Analysis [Abstract] [BibTeX] [URL]	2021 American Control Conference (ACC) , 917-922.	inproceedings
Abstract: Recently, a concurrent monitoring scheme based on slow feature analysis (SFA) has been developed to differentiate operating point changes with process dynamics. The original SFA algorithm requires the data to be fed in as a whole in the training stage and is unsuitable for an increasingly tremendous data volume in modern industries. Other variations have also been developed such as recursive slow feature analysis (RSFA) to process data sequentially, which, however, requires storing, updating, and decomposing two covariance matrices, and increases computational and memory costs. In this work, a new process monitoring scheme is proposed based on a covariance free incremental slow feature analysis (IncSFA) method, which handles massive data efficiently and has a linear feature updating complexity with respect to data dimensionality. The effectiveness of IncSFA-based monitoring method is demonstrated with the Tennessee Eastman Process.
BibTeX: @inproceedings{9482953, author = {Saafan, Hussein and Zhu, Qinqin}, title = {Comprehensive Monitoring with Incremental Slow Feature Analysis}, booktitle = {2021 American Control Conference (ACC)}, year = {2021}, pages = {917-922}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9482953}, doi = {http://doi.org/10.23919/ACC50511.2021.9482953} }
Schill	2009	Modellierung invarianter Ortserkennung mittels Slow Feature Analysis [BibTeX]	.	misc
BibTeX: @misc{Schill-2009, author = {Schill}, title = {Modellierung invarianter {O}rtserkennung mittels {S}low {F}eature {A}nalysis}, year = {2009} }
Schönfeld, F. & Wiskott, L.	2012	Spatial representation in the hippocampus [BibTeX]	Poster at the g-Node GPU Workshop, Apr 11--13, Munich, Germany .	misc
BibTeX: @misc{SchoenfeldWiskott-2012a, author = {Fabian Sch\"onfeld and Laurenz Wiskott}, title = {Spatial representation in the hippocampus}, year = {2012}, howpublished = {Poster at the g-Node GPU Workshop, Apr 11--13, Munich, Germany} }
Schönfeld, F. & Wiskott, L.	2012	Sensory integration of place and head-direction cells in a virtual environment [BibTeX]	Poster at the 8^th FENS Forum of Neuroscience, Jul 14--18, Barcelona, Spain .	misc
BibTeX: @misc{SchoenfeldWiskott-2012b, author = {Fabian Sch\"onfeld and Laurenz Wiskott}, title = {Sensory integration of place and head-direction cells in a virtual environment}, year = {2012}, howpublished = {Poster at the 8\textsuperscript{th} FENS Forum of Neuroscience, Jul 14--18, Barcelona, Spain} }
Schönfeld, F. & Wiskott, L.	2013	RatLab: an easy to use tool for place code simulations [Abstract] [BibTeX] [URL] [URL(2)]	Frontiers in Computational Neuroscience , 104(7).	article
Abstract: In this paper we present the RatLab toolkit, a software framework designed to set up and simulate a wide range of studies targeting the encoding of space in rats. It provides open access to our modeling approach to establish place and head direction cells within unknown environments and it offers a set of parameters to allow for the easy construction of a variety of enclosures for a virtual rat as well as controlling its movement pattern over the course of experiments. Once a spatial code is formed RatLab can be used to modify aspects of the enclosure or movement pattern and plot the effect of such modifications on the spatial representation, i.e., place and head direction cell activity. The simulation is based on a hierarchical Slow Feature Analysis (SFA) network that has been shown before to establish a spatial encoding of new environments using visual input data only. RatLab encapsulates such a network, generates the visual training data, and performs all sampling automatically—with each of these stages being further configurable by the user. RatLab was written with the intention to make our SFA model more accessible to the community and to that end features a range of elements to allow for experimentation with the model without the need for specific programming skills.
BibTeX: @article{SchoenfeldWiskott-2013a, author = {F. Sch\"onfeld and L. Wiskott}, title = {{RatLab}: an easy to use tool for place code simulations}, journal = {Frontiers in Computational Neuroscience}, year = {2013}, volume = {104}, number = {7}, url = {http://journal.frontiersin.org/article/10.3389/fncom.2013.00104/full}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/SchoenfeldWiskott-2013-FrontiersCompNeurosci-RatLab.pdf}, doi = {http://doi.org/10.3389/fncom.2013.00104} }
Schönfeld, F. & Wiskott, L.	2013	Theoretical neuroscience: finding your way into the light [BibTeX]	IGSN report , 47-49.	misc
BibTeX: @misc{SchoenfeldWiskott-2013b, author = {Fabian Sch\"onfeld and Laurenz Wiskott}, title = {Theoretical neuroscience: finding your way into the light}, journal = {IGSN report}, year = {2013}, pages = {47--49} }
Schönfeld, F. & Wiskott, L.	2015	Modeling place field activity with hierarchical slow feature analysis [Abstract] [BibTeX] [URL]	frontiers in Computational Neuroscience , 9(51).	article
Abstract: What are the computational laws of hippocampal activity? In this paper we argue for the slowness principle as a fundamental processing paradigm behind hippocampal place cell firing. We present six different studies from the experimental literature, performed with real-life rats, that we replicated in computer simulations. Each of the chosen studies allows rodents to develop stable place fields and then examines a distinct property of the established spatial encoding: adaptation to cue relocation and removal; directional dependent firing in the linear track and open field; and morphing and scaling the environment itself. Simulations are based on a hierarchical Slow Feature Analysis (SFA) network topped by a principal component analysis (ICA) output layer. The slowness principle is shown to account for the main findings of the presented experimental studies. The SFA network generates its responses using raw visual input only, which adds to its biological plausibility but requires experiments performed in light conditions. Future iterations of the model will thus have to incorporate additional information, such as path integration and grid cell activity, in order to be able to also replicate studies that take place during darkness.
BibTeX: @article{SchoenfeldWiskott-2015, author = {Fabian Sch{\"{o}}nfeld and Laurenz Wiskott}, title = {Modeling place field activity with hierarchical slow feature analysis}, journal = {frontiers in Computational Neuroscience}, year = {2015}, volume = {9}, number = {51}, url = {http://journal.frontiersin.org/article/10.3389/fncom.2015.00051/full}, doi = {http://doi.org/10.3389/fncom.2015.00051} }
Schüler, M.; Hlynsson, H.D. & Wiskott, L.	2019	Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening [Abstract] [BibTeX] [URL]	Proceedings of The Eleventh Asian Conference on Machine Learning , Proceedings of Machine Learning Research , 101, 316-331. Eds. Lee, W. S. & Suzuki, T. Publ. PMLR.	inproceedings
Abstract: We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and also for (c) a general dataset for which symmetric non-temporal similarities between points can be defined.
BibTeX: @inproceedings{pmlr-v101-schuler19a, author = {Sch{\"u}ler, Merlin and Hlynsson, Hlynur Dav\'i\dh and Wiskott, Laurenz}, title = {Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, publisher = {PMLR}, year = {2019}, volume = {101}, pages = {316--331}, url = {https://proceedings.mlr.press/v101/schuler19a.html} }
Schüler, M.; Hlynsson, H.D. & Wiskott, L.	2018	Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening [BibTeX]	CoRR , abs/1808.08833.	article
BibTeX: @article{SchuelerHlynssonEtAl-2018, author = {Merlin Sch{\"u}ler and Hlynur Dav{\'i}ð Hlynsson and Laurenz Wiskott}, title = {Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening}, journal = {CoRR}, year = {2018}, volume = {abs/1808.08833} }
Schüler, M.; Hlynsson, H.D. & Wiskott, L.	2018	Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening [BibTeX]	arXiv preprint arXiv:1808.08833 .	article
BibTeX: @article{SchuelerHlynssonEtAl-2018a, author = {Sch{\"u}ler, Merlin and Hlynsson, Hlynur Dav{\'\i}{\dh} and Wiskott, Laurenz}, title = {Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening}, journal = {arXiv preprint arXiv:1808.08833}, year = {2018} }
Schumann, M.	2011	Analyse und Vergleich von Algorithmen zur Bestimmung des optischen Flusses [BibTeX] [URL(2)]	Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, Institut für Informatik, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, Institut für Informatik .	mastersthesis
BibTeX: @mastersthesis{Schumann-2011, author = {Schumann, Martin}, title = {Analyse und {V}ergleich von {A}lgorithmen zur {B}estimmung des optischen {F}lusses}, school = {Humboldt-Universit{\"{a}}t zu Berlin, Mathematisch-Naturwissenschaftliche Fakult{\"{a}}t II, Institut f{\"{u}}r Informatik}, year = {2011}, url2 = {http://www.neurorobotics.eu/downloads/publications/2011%20Schumann%20-%20Analyse%20und%20Vergleich%20von%20Algorithmen%20zur%20Bestimmung%20des%20optischen%20Flusses.pdf} }
Schwartz, A.D.	2009	On the pattern classification of structured data using the neocortexinspired memory-prediction framework [Abstract] [BibTeX] [URL] [URL(2)]	Technical Report, University of Southern Denmark, Faculty of Engineering, Mærsk Mc-Kinney Møller Institute, Odense, Denmark, Sigma Space Corp. (090612).	mastersthesis
Abstract: In this master thesis project, we have researched how a theoretical model of the neo- cortex can be implemented as a hierarchical Bayesian network. The report is based on the theoretical Memory-prediction Framework (MPF) by Hawkins & Blakeslee (2004), which was later implemented in the Hierarchical Temporal Memory (HTM) by George & Hawkins (2005). The assumption of the master thesis project is that the HTM is unable to implement fundamental concepts of the MPF and is furthermore based on methods and tools that do not scale well with complexity when they are applied to realistic and complex problems. In this thesis we have been inspired by the work of Lee & Mumford (2003) and Dean (2006) in formulating an alternative model. The resulting novel Dynamic Hierarchical Nonparametric Belief Propagation (DHNBP) framework is based on the principals of the MPF framework and is able to facilitate representation of spatiotemporal sequences of features in a Dynamic Markov Network. The DHNBP framework is a novel extension of the Nonparametric Belief Propagation framework by Sudderth (2006) into hierarchies and time. In this report we provide algorithms for implementation, however, the DHNBP framework still has open-ended aspects that require further research
BibTeX: @mastersthesis{Schwartz-2009, author = {Schwartz, Anders Due}, title = {On the pattern classification of structured data using the neocortexinspired memory-prediction framework}, school = {University of Southern Denmark, Faculty of Engineering, M{\ae}rsk Mc-Kinney M{\o}ller Institute, Odense, Denmark}, year = {2009}, number = {090612}, url = {http://www.eing.dk/Files/Thesis.pdf}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.454.2875&rep=rep1&type=pdf} }
Shan, Y.; Zhang, Z. & Huang, K.	2014	Learning skeleton stream patterns with slow feature analysis for action recognition [Abstract] [BibTeX] [URL]	European Conference on Computer Vision , 111-121.	inproceedings
Abstract: Previous studies on MoCap (Motion Capturing (MoCap) System tracks the key points which are marked with conspicuous color or other materials (such as LED lights). The motion sequences are collected into MoCap action datasets, e.g., 1973 [3] and CMU [4] MoCap action datasets.) action data suggest that skeleton joint streams contain sufficient intrinsic information for understanding human body actions. With the advancement in depth sensors, e.g., Kinect, pose estimation with depth image provides more available realistic skeleton stream data. However, the locations of joints are always unstable due to noises. Moreover, as the estimated skeletons of different persons are not the same, the variance of intra-class is large. In this paper, we first expand the coordinate stream of each joint into multi-order streams by fusing hierarchical global information to improve the stability of joint streams. Then, Slow Feature Analysis is applied to learn the visual pattern of each joint, and the high-level information in the learnt general patterns is encoded into each skeleton to reduce the intra-variance of the skeletons. Temporal pyramid of posture word histograms is used to describe the global temporal information of action sequence. Our approach is verified with Support Vector Machine (SVM) classifier on MSR Action3D dataset, and the experimental results demonstrate that our approach achieves the state-of-the-art level.
BibTeX: @inproceedings{ShanZhangEtAl-2014, author = {Shan, Yanhu and Zhang, Zhang and Huang, Kaiqi}, title = {Learning skeleton stream patterns with slow feature analysis for action recognition}, booktitle = {European Conference on Computer Vision}, year = {2014}, pages = {111--121}, url = {http://link.springer.com/chapter/10.1007/978-3-319-16199-0_8}, doi = {http://doi.org/10.1007/978-3-319-16199-0_8} }
Shan, Y.; Zhang, Z.; Wang, S.; Huang, K. & Tan, T.	2011	Surveillance event detection [Abstract] [BibTeX] [URL(2)]	IRDS-CASIA at TRECVid 2011, Benchmarking Activity .	inproceedings
Abstract: This paper proposes the event detection system for TRECVid 2011 surveillance event detection. ”CellToEar”, ”Embrace”, ”ObjectPut”, ”PeopleMeet”, ”PeopleSplit- Up”, ”PersonRuns” and ”Pointing” are the 7 events we detect in our system. Firstly, interest points are detected in the Local spatial and temporal regions, and local feature is described with SFA (slow feature analysis) method. We apply lib-SVM to classify the 7 events and the 7 scores cor- responding to foregoing events are the original result of the local region. Post-processing is used to generate the global result and reduce the false alarm.
BibTeX: @inproceedings{ShanZhangEtAl-2011, author = {Shan, Yanhu and Zhang, Zhang and Wang, Shiquan and Huang, Kaiqi and Tan, Tieniu}, title = {Surveillance event detection}, booktitle = {IRDS-CASIA at TRECVid 2011, Benchmarking Activity}, year = {2011}, url2 = {https://pdfs.semanticscholar.org/7a32/2fb1426e67adcbd6c7c0650e2dbc418fc367.pdf} }
Shang, C.; Huang, B.; Lu, Y.; Yang, F. & Huang, D.	2016	Dynamic modeling of gross errors via probabilistic slow feature analysis applied to a mining slurry preparation process [BibTeX] [URL(2)]	IFAC-PapersOnLine , 49(20), 25-30. Publ. Elsevier.	article
BibTeX: @article{ShangHuangEtAl-2016b, author = {Shang, Chao and Huang, Biao and Lu, Yaojie and Yang, Fan and Huang, Dexian}, title = {Dynamic modeling of gross errors via probabilistic slow feature analysis applied to a mining slurry preparation process}, journal = {IFAC-PapersOnLine}, publisher = {Elsevier}, year = {2016}, volume = {49}, number = {20}, pages = {25--30}, url2 = {https://www.researchgate.net/profile/Chao_Shang2/publication/310390674_Dynamic_Modeling_of_Gross_Errors_via_Probabilistic_Slow_Feature_Analysis_Applied_to_a_Mining_Slurry_Preparation_Process/links/582dc5f908ae102f072da843.pdf} }
Shang, C.; Huang, B.; Yang, F. & Huang, D.	2015	Probabilistic slow feature analysis-based representation learning from massive process data for soft sensor modeling [Abstract] [BibTeX] [URL] [URL(2)]	AIChE Journal , 61(12), 4126-4139. Publ. Wiley Online Library.	article
Abstract: Latent variable (LV) models provide explicit representations of underlying driving forces of process variations and retain the dominant information of process data. In this study, slow features (SFs) as temporally correlated LVs are derived using probabilistic SF analysis. SFs evolving in a state-space form effectively represent nominal variations of processes, some of which are potentially correlated to quality variables and hence help improving the prediction performance of soft sensors. An efficient expectation maximum algorithm is proposed to estimate parameters of the probabilistic model, which turns out to be suitable for analyzing massive process data. Two criteria are also proposed to select quality-relevant SFs. The validity and advantages of the proposed method are demonstrated via two case studies. © 2015 American Institute of Chemical Engineers AIChE J, 61: 4126–4139, 2015
BibTeX: @article{ShangHuangEtAl-2015, author = {Shang, Chao and Huang, Biao and Yang, Fan and Huang, Dexian}, title = {Probabilistic slow feature analysis-based representation learning from massive process data for soft sensor modeling}, journal = {AIChE Journal}, publisher = {Wiley Online Library}, year = {2015}, volume = {61}, number = {12}, pages = {4126--4139}, url = {http://onlinelibrary.wiley.com/doi/10.1002/aic.14937/abstract}, url2 = {https://www.researchgate.net/profile/Chao_Shang2/publication/280917378_Probabilistic_Slow_Feature_Analysis-Based/links/55cb724708aeb975674c7ab6.pdf}, doi = {http://doi.org/10.1002/aic.14937} }
Shang, C.; Huang, B.; Yang, F. & Huang, D.	2016	Slow feature analysis for monitoring and diagnosis of control performance [Abstract] [BibTeX] [URL] [URL(2)]	Journal of Process Control , 39, 21-34. Publ. Elsevier.	article
Abstract: Recently, slow feature analysis (SFA), a novel dimensionality reduction technique, has been adopted for integrated monitoring of operating condition and process dynamics. By isolating temporal behaviors from steady-state information, the SFA-based monitoring scheme enables improved discrimination of nominal operating point changes from real faults. In this study, we demonstrate that the temporal dynamics is an additional indicator of control performance changes, and further exploit its unique efficacy in control performance monitoring. Because of its data-driven nature and ease from first-principle knowledge, the SFA-based monitoring scheme allows an overall assessment of the plant-wide control performance and is compatible with different control strategies. An attractive feature of the SFA-based approach compared to existing ones is that generic process monitoring indices are used, which renders contribution plots naturally applicable to real-time diagnosis of control performance. As a result, potential fault variables as root causes of control performance changes can be identified, including not only controlled variables (CV) but also manipulated variables (MV) and disturbance variables (DV). Simulated and experimental studies demonstrate the effectiveness of the proposed method.
BibTeX: @article{ShangHuangEtAl-2016a, author = {Shang, Chao and Huang, Biao and Yang, Fan and Huang, Dexian}, title = {Slow feature analysis for monitoring and diagnosis of control performance}, journal = {Journal of Process Control}, publisher = {Elsevier}, year = {2016}, volume = {39}, pages = {21--34}, url = {http://www.sciencedirect.com/science/article/pii/S0959152415002309}, url2 = {https://www.researchgate.net/profile/Chao_Shang2/publication/290480641_Slow_feature_analysis_for_monitoring_and_diagnosis_of_control_performance/links/5699a63d08ae748dfaff8e4d.pdf}, doi = {http://doi.org/10.1016/j.jprocont.2015.12.004} }
Shang, C.; Huang, X.; Yang, F. & Huang, D.	2019	Sparse Slow Feature Analysis for Enhanced Control Monitoring and Fault Isolation [Abstract] [BibTeX] [URL]	2019 1st International Conference on Industrial Artificial Intelligence (IAI) , 1-6.	inproceedings
Abstract: This paper presents sparse slow feature analysis (SFA) for efficient process monitoring and fault isolation, which is a new latent variable model for time series data. We first recast sparse SFA in terms of a novel regression-type problem, and further incorporate l1-norm penalty into the objective in order to promote sparsity. To solve the induced nonconvex optimization problem, a tailored iterative algorithm is developed. With the sparse representation, process variables with insignificant contributions can be completely omitted, and each latent variable relates only to a fraction of crucial process variables in comparison with the generic SFA. A new process monitoring and fault isolation approach is developed based on the sparse SFA, which results in improved monitoring performance, easy-to-interpret diagnostics, and meaningful process knowledge discovery. Case studies on the Tennessee Eastman process are carried out to address the applicability of the proposed approach.
BibTeX: @inproceedings{8850796, author = {Shang, Chao and Huang, Xiaolin and Yang, Fan and Huang, Dexian}, title = {Sparse Slow Feature Analysis for Enhanced Control Monitoring and Fault Isolation}, booktitle = {2019 1st International Conference on Industrial Artificial Intelligence (IAI)}, year = {2019}, pages = {1-6}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8850796}, doi = {http://doi.org/10.1109/ICIAI.2019.8850796} }
Shang, C.; Yang, F.; Gao, X. & Huang, D.	2015	Extracting latent dynamics from process data for quality prediction and performance assessment via slow feature regression [Abstract] [BibTeX] [URL] [URL(2)]	2015 American Control Conference (ACC) , 912-917.	inproceedings
Abstract: Latent variable (LV) models such as partial least squares (PLS) have been widely used to derive low-dimensional subspaces and build regression models in process control problems, especially in quality prediction tasks. However, they are based on the assumption that industrial processes operate at steady states, thereby ignoring process dynamics. In this article, slow feature regression (SFR), a novel linear regression model with LV subspaces, is proposed, which consists of two steps. In the first step, slow features as LVs are extracted via slow feature analysis (SFA), a rising machine learning methodology. Different from classical LV models, SFA assumes LVs have slowly varying dynamics, which can be derived by analyzing the temporal structure within abundant process data. Owing to evident dynamics in industrial processes, slowness can be considered as a valid prior knowledge to utilize. In the second step, the slowest features are selected as a reasonable description of processes to further predict the product quality, which is also likely to be slowly varying. In addition to the Hotelling's T2 statistic, a novel S2 index is proposed to evaluate the dynamic variations within processes and assess the real-time performance of the prediction model. The effectiveness of the SFR-based approach is demonstrated through an application in the Tennessee Eastman process.
BibTeX: @inproceedings{ShangYangEtAl-2015b, author = {Shang, Chao and Yang, Fan and Gao, Xinqing and Huang, Dexian}, title = {Extracting latent dynamics from process data for quality prediction and performance assessment via slow feature regression}, booktitle = {2015 American Control Conference (ACC)}, year = {2015}, pages = {912--917}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7170850}, url2 = {https://www.researchgate.net/profile/Chao_Shang2/publication/282792391_Extracting_latent_dynamics_from_process_data_for_quality_prediction_and_performance_assessment_via_slow_feature_regression/links/5651b95408aefe619b182d21.pdf}, doi = {http://doi.org/10.1109/acc.2015.7170850} }
Shang, C.; Yang, F.; Gao, X.; Huang, X.; Suykens, J.A.K. & Huang, D.	2015	Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	AIChE Journal , 61(11), 3666-3682. Publ. Wiley Online Library.	article
Abstract: Latent variable (LV) models have been widely used in multivariate statistical process monitoring. However, whatever deviation from nominal operating condition is detected, an alarm is triggered based on classical monitoring methods. Therefore, they fail to distinguish real faults incurring dynamics anomalies from normal deviations in operating conditions. A new process monitoring strategy based on slow feature analysis (SFA) is proposed for the concurrent monitoring of operating point deviations and process dynamics anomalies. Slow features as LVs are developed to describe slowly varying dynamics, yielding improved physical interpretation. In addition to classical statistics for monitoring deviation from design conditions, two novel indices are proposed to detect anomalies in process dynamics through the slowness of LVs. The proposed approach can distinguish whether the changes in operating conditions are normal or real faults occur. Two case studies show the validity of the SFA-based process monitoring approach. © 2015 American Institute of Chemical Engineers AIChE J, 61: 3666–3682, 2015
BibTeX: @article{ShangYangEtAl-2015a, author = {Shang, Chao and Yang, Fan and Gao, Xinqing and Huang, Xiaolin and Suykens, Johan AK and Huang, Dexian}, title = {Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis}, journal = {AIChE Journal}, publisher = {Wiley Online Library}, year = {2015}, volume = {61}, number = {11}, pages = {3666--3682}, url = {http://onlinelibrary.wiley.com/doi/10.1002/aic.14888/abstract}, url2 = {https://www.researchgate.net/profile/Chao_Shang2/publication/277088372_Concurrent_Monitoring_of_Operating_Condition_Deviations_and_Process_Dynamics_Anomalies_with_Slow_Feature_Analysis/links/55620f3708ae86c06b65f05b.pdf}, doi = {http://doi.org/10.1002/aic.14888} }
Shang, C.; Yang, F. & Huang, D.	2018	A Systematic Approach to Dynamic Monitoring of Industrial Processes Based on Second-Order Slow Feature Analysis⁎⁎This work is supported in part by the National Natural Science Foundation of China (Nos. 61673236 and 61433001), the National Basic Research Program of China (No. 2012CB720505). [Abstract] [BibTeX] [URL]	IFAC-PapersOnLine , 51(18), 387-392.	article
Abstract: Slow feature analysis has proven to be an effective process monitoring and fault diagnosis approach. By isolating temporal behaviors from steady-state variations in process data, slow feature analysis enables a concurrent monitoring of operating condition and process dynamics, based on which false alarms triggered by nominal operating condition deviations can be effectively removed. However, the present formulation of slow feature analysis only makes use of the first-order time difference of time series data, thereby falling short of addressing high-order dynamics in process operations. In this work, we propose a second-order formulation of slow feature analysis, and further develop a systematic framework for process monitoring and fault diagnosis, which can provide more meaningful information about process dynamics to assist decision-making of operators. Case studies on the Tennessee Eastman benchmark process are conducted to demonstrate the efficacy of the proposed method.
BibTeX: @article{SHANG2018387, author = {Chao Shang and Fan Yang and Dexian Huang}, title = {A Systematic Approach to Dynamic Monitoring of Industrial Processes Based on Second-Order Slow Feature Analysis⁎⁎This work is supported in part by the National Natural Science Foundation of China (Nos. 61673236 and 61433001), the National Basic Research Program of China (No. 2012CB720505).}, journal = {IFAC-PapersOnLine}, year = {2018}, volume = {51}, number = {18}, pages = {387-392}, url = {https://www.sciencedirect.com/science/article/pii/S2405896318320147}, doi = {http://doi.org/10.1016/j.ifacol.2018.09.331} }
Shang, C.; Yang, F. & Huang, D.	2018	A Systematic Approach to Dynamic Monitoring of Industrial Processes Based on Second-Order Slow Feature Analysis [BibTeX]	IFAC-PapersOnLine , 51(18), 387-392. Publ. Elsevier.	article
BibTeX: @article{ShangYangEtAl-2018a, author = {Shang, Chao and Yang, Fan and Huang, Dexian}, title = {A Systematic Approach to Dynamic Monitoring of Industrial Processes Based on Second-Order Slow Feature Analysis}, journal = {IFAC-PapersOnLine}, publisher = {Elsevier}, year = {2018}, volume = {51}, number = {18}, pages = {387--392}, doi = {http://doi.org/10.1016/j.ifacol.2018.09.331} }
Shang, C.G.; Yang, F.; Huang, B. & Huang, D.	2018	Recursive Slow Feature Analysis for Adaptive Monitoring of Industrial Processes [BibTeX]	IEEE Transactions on Industrial Electronics , 65, 8895-8905.	article
BibTeX: @article{ShangYangEtAl-2018, author = {C. G. Shang and Fan Yang and Biao Huang and Dexian Huang}, title = {Recursive Slow Feature Analysis for Adaptive Monitoring of Industrial Processes}, journal = {IEEE Transactions on Industrial Electronics}, year = {2018}, volume = {65}, pages = {8895-8905}, doi = {http://doi.org/10.1109/tie.2018.2811358} }
Shang, L.; Wang, Y.; Deng, X.; Cao, Y.; Wang, P. & Wang, Y.	2019	A Model Predictive Control Performance Monitoring and Grading Strategy Based on Improved Slow Feature Analysis [Abstract] [BibTeX] [URL]	IEEE Access , 7, 50897-50911.	article
Abstract: Slow feature analysis (SFA) has been adopted for control performance monitoring (CPM) recently. However, due to the selection criterion of the dominant slow features (SFs) and the performance monitoring statistics, the traditional SFA-based CPM method has certain limitations in monitoring model predictive control (MPC) performance and fails to distinguish the direction of performance change, i.e., whether the performance becomes better or worse. In order to solve the above problems, an MPC performance monitoring and grading strategy based on improved SFA is proposed in this paper. First, a new criterion for selecting dominant SFs is proposed. On this basis, two combined monitoring indices are built to monitor steady-state and dynamic characteristics of MPC systems, respectively. Besides, an SFA-based predictable performance assessment index is proposed to indicate the direction of performance change. Finally, a performance grading strategy based on improved SFA is established to classify current MPC performance to four levels. Two simulation examples demonstrate the effectiveness and superiority of the proposed method.
BibTeX: @article{8691760, author = {Shang, Linyuan and Wang, Yanjiang and Deng, Xiaogang and Cao, Yuping and Wang, Ping and Wang, Yuhong}, title = {A Model Predictive Control Performance Monitoring and Grading Strategy Based on Improved Slow Feature Analysis}, journal = {IEEE Access}, year = {2019}, volume = {7}, pages = {50897-50911}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8691760}, doi = {http://doi.org/10.1109/ACCESS.2019.2911369} }
Shang, L.; Wang, Y.; Deng, X.; Cao, Y.; Wang, P. & Wang, Y.	2019	An Enhanced Method to Assess MPC Performance Based on Multi-Step Slow Feature Analysis [Abstract] [BibTeX] [URL]	Energies , 12(19).	article
Abstract: Due to the wide application of model predictive control (MPC) in industrial processes, the assessment of MPC performance is essential to ensure product quality and improve energy efficiency. Recently, the slow feature analysis (SFA) algorithm has been successfully applied to assess the performance of MPC. However, the disadvantage of the traditional SFA-based predictable index is that it can only extract one-step predictable information in the monitored variables. In order to better mine the predictable information contained in the monitored variables with large lag, an enhanced method to assess MPC performance based on multi-step SFA (MSSFA) is proposed. Based on the relationship between the slowness of slow features (SFs) and data predictability, an MSSFA model SFA(τ) is built through extending the temporal derivatives of the SFs from one step to multiple steps to extract multi-step predictable information in the monitored variables, which is used to construct a multi-step predictable index. Then, the predictable information in the SFs is further extracted for enhancing the multi-step predictable index to improve its sensitivity to performance changes. The effectiveness of the proposed method has been verified through two process simulation examples.
BibTeX: @article{en12193799, author = {Shang, Linyuan and Wang, Yanjiang and Deng, Xiaogang and Cao, Yuping and Wang, Ping and Wang, Yuhong}, title = {An Enhanced Method to Assess MPC Performance Based on Multi-Step Slow Feature Analysis}, journal = {Energies}, year = {2019}, volume = {12}, number = {19}, url = {https://www.mdpi.com/1996-1073/12/19/3799}, doi = {http://doi.org/10.3390/en12193799} }
Shaw, J.	2005	Predictive coding with temporal invariance [BibTeX] [URL]	techreport, The University of Rochester, Computer Science Department, The University of Rochester, Computer Science Department (859).	techreport
BibTeX: @techreport{Shaw-2005, author = {Shaw, Jonathan}, title = {Predictive coding with temporal invariance}, school = {The University of Rochester, Computer Science Department}, year = {2005}, number = {859}, url = {ftp://cs.rochester.edu/pub/papers/robotics/05.tr859.Predictive_coding_with_temporal_invariance.pdf} }
Shaw, J.M.	2006	Unifying perception and curiosity [Abstract] [BibTeX] [URL] [URL(2)]	University of Rochester, University of Rochester .	phdthesis
Abstract: There has been much research in recent decades aimed at discovering what the underlying principles are, if any, that drive the brain. As the cortex appears to be basically uniform, it seems that if there is an underlying principle, it is ubiquitous. However, the principles which have been proposed to explain the brain have largely been specialized principles, which each explain a particular aspect of the brain. Principles such as efficient coding, predictive coding, and temporal invariance have been proposed to explain sensory coding, and have succeeded to some measure in reproducing the receptive field properties of neurons in the visual cortex. Bayesian surprise has been offered as an explanation of attention, and has enjoyed some success in modeling human saccades, while reinforcement learning and intelligent adaptive curiosity have been aimed at explaining how actions are chosen. In this dissertation we propose a novel principle which we call predictive action. It is an information theoretic principle which unifies all of the above proposals. We show its relationship to each of the above proposals, and give several algorithms which approximate predictive action for specific environments. We hope that this principle will allow not only for a greater understanding of the brain, but also serve as a principled basis for the design of future algorithms to solve a broad range of problems in artificial intelligence.
BibTeX: @phdthesis{Shaw-2006, author = {Shaw, Jonathan M}, title = {Unifying perception and curiosity}, school = {University of Rochester}, year = {2006}, url = {ftp://anon.cs.rochester.edu/pub/papers/robotics/06.tr897thesis.Unifying_perception_and_curiosity.pdf}, url2 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.329.5640&rep=rep1&type=pdf} }
Si, Y.; Liu, D.; Yang, H.; Li, Z. & Wang, Y.	2019	Transient Stability Assessment of Power Systems Based on Slow Feature Analysis [BibTeX] [URL]	2019 Chinese Control Conference (CCC) , 7334-7339.	inproceedings
BibTeX: @inproceedings{8865842, author = {Si, Yabin and Liu, Daowei and Yang, Hongying and Li, Zonghan and Wang, Youqing}, title = {Transient Stability Assessment of Power Systems Based on Slow Feature Analysis}, booktitle = {2019 Chinese Control Conference (CCC)}, year = {2019}, pages = {7334-7339}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8865842}, doi = {http://doi.org/10.23919/ChiCC.2019.8865842} }
Si, Y. & Wang, Y.	2019	Two-Step Dynamic Slow Feature Analysis for Dynamic Process Monitoring [Abstract] [BibTeX] [URL]	2019 1st International Conference on Industrial Artificial Intelligence (IAI) , 1-6.	inproceedings
Abstract: Many successful classical multivariate statistical process monitoring (MSPM) approaches have been applied in industrial processes. However, most of these methods and their extended dynamic versions fail to distinguish real faults incurring dynamic anomalies from normal changes in operating conditions in process dynamics. One popular solution is based on slow feature analysis (SFA) and dynamic SFA (DSFA). Notice that SFA and DSFA use a pair of statistics for monitoring dynamic processes without considering dynamic structure. In this study, a two-step DSFA (TS-DSFA) is proposed for monitoring dynamic processes. TS-DSFA firstly separates dynamic components from dynamic processes, and then constructs a evaluation model of dynamic processes. TS-DSFA assists in distinguishing real faults from normal changes in operating conditions, and it shows good performance in monitoring dynamic processes with uncertain noises. Finally, a numerical case is presented to verify the effectiveness of the TS-DSFA.
BibTeX: @inproceedings{8850780, author = {Si, Yabin and Wang, Youqing}, title = {Two-Step Dynamic Slow Feature Analysis for Dynamic Process Monitoring}, booktitle = {2019 1st International Conference on Industrial Artificial Intelligence (IAI)}, year = {2019}, pages = {1-6}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=8850780}, doi = {http://doi.org/10.1109/ICIAI.2019.8850780} }
Sprague, N.	2013	Contingent feature analysis [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Applying reinforcement learning algorithms in real-world domains is challeng- ing because relevant state information is often embedded in a stream of high- dimensional sensor data. This paper describes a novel algorithm for learning task- relevant features through interactions with the environment. The key idea is that a feature is likely to be useful to the degree that its dynamics can be controlled by the actions of the agent. We describe an algorithm that can find such features and we demonstrate its effectiveness in an artificial domain.
BibTeX: @misc{Sprague-2013, author = {Sprague, Nathan}, title = {Contingent feature analysis}, year = {2013}, url2 = {http://acl.mit.edu/amlsc/files/amlsc13_submission_9.pdf} }
Sprague, N.	2014	Contingent features for reinforcement learning [Abstract] [BibTeX] [URL] [URL(2)]	International Conference on Artificial Neural Networks , 347-354.	inproceedings
Abstract: Applying reinforcement learning algorithms in real-world domains is challenging because relevant state information is often embedded in a stream of high-dimensional sensor data. This paper describes a novel algorithm for learning task-relevant features through interactions with the environment. The key idea is that a feature is likely to be useful to the degree that its dynamics can be controlled by the actions of the agent. We describe an algorithm that can find such features and we demonstrate its effectiveness in an artificial domain.
BibTeX: @inproceedings{Sprague-2014, author = {Sprague, Nathan}, title = {Contingent features for reinforcement learning}, booktitle = {International Conference on Artificial Neural Networks}, year = {2014}, pages = {347--354}, url = {http://link.springer.com/chapter/10.1007/978-3-319-11179-7_44}, url2 = {https://w3.cs.jmu.edu/spragunr/papers/icann2014.pdf}, doi = {http://doi.org/10.1007/978-3-319-11179-7_44} }
Spranger, M.; Höfer, S. & Hild, M.	2009	Biologically inspired posture recognition and posture change detection for humanoid robots [Abstract] [BibTeX] [URL] [URL(2)]	2009 IEEE International Conference on Robotics and Biomimetics (ROBIO) , 562-567. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: This paper presents a biologically inspired ap- proach to posture recognition and posture change detection for a biped robot. Slow Feature Analysis, an algorithm developed by theoretical biologists for extracting slowly changing signals from signals varying on a fast time scale, is applied to the problem of recognizing the posture of biped humanoid robots over time and successively on the recognition of the change of posture. Both the recognition of basic static postures, like lying and standing, of peer robots via visual sensory information and the recognition of the same postures via internal proprioceptive sensors are considered. Given promising results in this domain we extend the application of the method onto the dynamic domain of detecting the change of posture, specifically we show the utility of the algorithm for detecting when a robot falls.
BibTeX: @inproceedings{SprangerHoeferEtAl-2009, author = {Spranger, Michael and H{\"o}fer, Sebastian and Hild, Manfred}, title = {Biologically inspired posture recognition and posture change detection for humanoid robots}, booktitle = {2009 {IEEE} International Conference on Robotics and Biomimetics ({ROBIO})}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2009}, pages = {562--567}, url = {http://ieeexplore.ieee.org/document/5420708/}, url2 = {http://neurorobotics.de/downloads/publications/2009%20Spranger%20-%20Biologically%20Inspired%20Posture%20Recognition%20and%20Detection.pdf}, doi = {http://doi.org/10.1109/robio.2009.5420708} }
Sprekeler, H.	2009	Slowness learning. [Abstract] [BibTeX] [URL]	Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät I .	phdthesis
Abstract: In this thesis, we investigate slowness as an unsupervised learning principle of sensory processing. Two aspects are given particular emphasis: (a) the mathematical analysis of Slow Feature Analysis (SFA) as one particular implementation of slowness learning and (b) the question, how slowness learning can be implemented in a biologically plausible fashion. In the first part of the thesis, we develop a mathematical framework for SFA and show that the optimal functions for SFA are the solutions of a partial differential eigenvalue problem. The theory allows (a) to make analytical predictions for the behavior of complicated applications and (b) an intuitive understanding of how the statistics of the input data are reflected in the optimal functions of SFA. The theory is applied to the learning of place and head-direction representations and to the learning of complex cell receptive fields as found in primary visual cortex. As a technical application, we use the theoretical results to develop and test a new algorithm for nonlinear blind source separation. The first part of the thesis is concluded by an information-theoretic analysis of the relation between slowness learning and predictive coding. In the second part of the thesis, we study the question, how slowness learning could be implemented in a biologically plausible manner. To this end, we first show that spike timing-dependent plasticity can under certain conditions be interpreted as an implementation of slowness learning. Finally, we show that both gradient-based slowness learning and spike timing-dependent plasticity lead to receptive field dynamics that can be described in terms of reaction-diffusion equations.
BibTeX: @phdthesis{Sprekeler-2009, author = {Henning Sprekeler}, title = {Slowness learning.}, school = {Humboldt-Universit{\"{a}}t zu Berlin, Mathematisch-Naturwissenschaftliche Fakult{\"{a}}t I}, year = {2009}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?id=29695} }
Sprekeler, H.	2011	On the relation of slow feature analysis and Laplacian eigenmaps [Abstract] [BibTeX] [URL]	Neural Computation , 23(12), 3287-3302. Publ. MIT Press - Journals.	article
Abstract: The past decade has seen a rise of interest in Laplacian eigenmaps (LEMs) for nonlinear dimensionality reduction. LEMs have been used in spectral clustering, in semisupervised learning, and for providing efficient state representations for reinforcement learning. Here, we show that LEMs are closely related to slow feature analysis (SFA), a biologically inspired, unsupervised learning algorithm originally designed for learning invariant visual representations. We show that SFA can be interpreted as a function approximation of LEMs, where the topological neighborhoods required for LEMs are implicitly defined by the temporal structure of the data. Based on this relation, we propose a generalization of SFA to arbitrary neighborhood relations and demonstrate its applicability for spectral clustering. Finally, we review previous work with the goal of providing a unifying view on SFA and LEMs.
BibTeX: @article{Sprekeler-2011, author = {Henning Sprekeler}, title = {On the relation of slow feature analysis and {L}aplacian eigenmaps}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2011}, volume = {23}, number = {12}, pages = {3287--3302}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00214}, doi = {http://doi.org/10.1162/NECO_a_00214} }
Sprekeler, H.; Michaelis, C. & Wiskott, L.	2006	Slowness: an objective for spike-timing dependent plasticity? [BibTeX]	Proc. 2^nd Bernstein Symposium for Computational Neuroscience, Oct 1-3, Berlin, Germany , 24. Publ. Bernstein Center for Computational Neuroscience (BCCN) Berlin.	inproceedings
BibTeX: @inproceedings{SprekelerMichaelisEtAl-2006a, author = {Henning Sprekeler and Christian Michaelis and Laurenz Wiskott}, title = {Slowness: an objective for spike-timing dependent plasticity?}, booktitle = {Proc.\ 2\textsuperscript{nd} Bernstein Symposium for Computational Neuroscience, Oct 1--3, Berlin, Germany}, publisher = {Bernstein Center for Computational Neuroscience (BCCN) Berlin}, year = {2006}, pages = {24} }
Sprekeler, H.; Michaelis, C. & Wiskott, L.	2006	Slowness: an objective for spike-timing-dependent plasticity? [Abstract] [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 5281.	misc
Abstract: Slow Feature Analysis (SFA) is an efficient algorithm for learning input-output functions that extract the most slowly varying features from a quickly varying signal. It has been successfully applied to the unsupervised learning of translation-, rotation-, and other invariances in a model of the visual system, to the learning of complex cell receptive fields, and, combined with a sparseness objective, to the self-organized formation of place cells in a model of the hippocampus. In order to arrive at a biologically more plausible implementation of this learning rule, we consider analytically how SFA could be realized in simple linear continuous and spiking model neurons. It turns out that for the continuous model neuron SFA can be implemented by means of a modified version of standard Hebbian learning. In this framework we provide a connection to the trace learning rule for invariance learning. We then show that for Poisson neurons spike-timing-dependent plasticity (STDP) with a specific learning window can learn the same weight distribution as SFA. Surprisingly, we find that the appropriate learning rule reproduces the typical STDP learning window. The shape as well as the timescale are in good agreement with what has been measured experimentally. This offers a completely novel interpretation for the functional role of spike-timing-dependent plasticity in physiological neurons.
BibTeX: @misc{SprekelerMichaelisEtAl-2006b, author = {Henning Sprekeler and Christian Michaelis and Laurenz Wiskott}, title = {Slowness: an objective for spike-timing-dependent plasticity?}, year = {2006}, volume = {5281}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/5281/} }
Sprekeler, H.; Michaelis, C. & Wiskott, L.	2007	Slowness: an objective for spike timing-dependent plasticity? [BibTeX]	Proc. 7^th Göttingen Meeting of the German Neuroscience Society, Mar 29 - Apr 1, Göttingen, Germany , T27-3A.	inproceedings
BibTeX: @inproceedings{SprekelerMichaelisEtAl-2007a, author = {Henning Sprekeler and Christian Michaelis and Laurenz Wiskott}, title = {Slowness: an objective for spike timing-dependent plasticity?}, booktitle = {Proc.\ 7\textsuperscript{th} G\"ottingen Meeting of the German Neuroscience Society, Mar 29 -- Apr 1, G\"ottingen, Germany}, year = {2007}, pages = {T27--3A} }
Sprekeler, H.; Michaelis, C. & Wiskott, L.	2007	Slowness: an objective for spike-timing-dependent plasticity? [Abstract] [BibTeX] [URL] [URL(2)]	PLoS Computational Biology , 3(6), e112.	article
Abstract: Our nervous system can efficiently recognize objects in spite of changes in contextual variables such as perspective or lighting conditions. Several lines of research have proposed that this ability for invariant recognition is learned by exploiting the fact that object identities typically vary more slowly in time than contextual variables or noise. Here, we study the question of how this "temporal stability" or "slowness" approach can be implemented within the limits of biologically realistic spike-based learning rules. We first show that slow feature analysis, an algorithm that is based on slowness, can be implemented in linear continuous model neurons by means of a modified Hebbian learning rule. This approach provides a link to the trace rule, which is another implementation of slowness learning. Then, we show analytically that for linear Poisson neurons, slowness learning can be implemented by spike-timing-dependent plasticity (STDP) with a specific learning window. By studying the learning dynamics of STDP, we show that for functional interpretations of STDP, it is not the learning window alone that is relevant but rather the convolution of the learning window with the postsynaptic potential. We then derive STDP learning windows that implement slow feature analysis and the "trace rule." The resulting learning windows are compatible with physiological data both in shape and timescale. Moreover, our analysis shows that the learning window can be split into two functionally different components that are sensitive to reversible and irreversible aspects of the input statistics, respectively. The theory indicates that irreversible input statistics are not in favor of stable weight distributions but may generate oscillatory weight dynamics. Our analysis offers a novel interpretation for the functional role of STDP in physiological neurons.
BibTeX: @article{SprekelerMichaelisEtAl-2007b, author = {Henning Sprekeler and Christian Michaelis and Laurenz Wiskott}, title = {Slowness: an objective for spike-timing--dependent plasticity?}, journal = {PLoS Computational Biology}, year = {2007}, volume = {3}, number = {6}, pages = {e112}, url = {http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.0030112}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/SprekelerMichaelisEtAl-2007b-PLoSCompBiol-SFA-STDP.pdf}, doi = {http://doi.org/10.1371/journal.pcbi.0030112} }
Sprekeler, H. & Wiskott, L.	2006	Analytical derivation of complex cell properties from the slowness principle. [BibTeX]	Proc. Berlin Neuroscience Forum, Jun 8-10, Bad Liebenwalde, Germany , 65-66. Publ. Max-Delbrück-Centrum für Molekulare Medizin (MDC), Berlin.	inproceedings
BibTeX: @inproceedings{SprekelerWiskott-2006a, author = {H. Sprekeler and L. Wiskott}, title = {Analytical derivation of complex cell properties from the slowness principle.}, booktitle = {Proc.\ Berlin Neuroscience Forum, Jun 8--10, Bad Liebenwalde, Germany}, publisher = {Max-Delbr\"uck-Centrum f\"ur Molekulare Medizin (MDC)}, year = {2006}, pages = {65--66} }
Sprekeler, H. & Wiskott, L.	2006	Analytical derivation of complex cell properties from the slowness principle. [BibTeX]	Proc. 15^th Annual Computational Neuroscience Meeting (CNS'06), Jul 16-20, Edinburgh, Scotland .	inproceedings
BibTeX: @inproceedings{SprekelerWiskott-2006b, author = {Sprekeler, Henning and Wiskott, Laurenz}, title = {Analytical derivation of complex cell properties from the slowness principle.}, booktitle = {Proc.\ 15\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'06), Jul 16--20, Edinburgh, Scotland}, year = {2006} }
Sprekeler, H. & Wiskott, L.	2006	Analytical derivation of complex cell properties from the slowness principle. [BibTeX]	Proc. Conference on Mathematical Neuroscience (NEUROMATH 06), Sep 1-4, Andorra , 62.	inproceedings
BibTeX: @inproceedings{SprekelerWiskott-2006c, author = {Henning Sprekeler and Laurenz Wiskott}, title = {Analytical derivation of complex cell properties from the slowness principle.}, booktitle = {Proc. Conference on Mathematical Neuroscience (NEUROMATH 06), Sep 1-4, Andorra}, year = {2006}, pages = {62} }
Sprekeler, H. & Wiskott, L.	2006	Analytical derivation of complex cell properties from the slowness principle. [BibTeX]	Proc. 2^nd Bernstein Symposium for Computational Neuroscience, Oct 1-3, Berlin, Germany , 67. Publ. Bernstein Center for Computational Neuroscience (BCCN) Berlin.	inproceedings
BibTeX: @inproceedings{SprekelerWiskott-2006d, author = {Henning Sprekeler and Laurenz Wiskott}, title = {Analytical derivation of complex cell properties from the slowness principle.}, booktitle = {Proc.\ 2\textsuperscript{nd} Bernstein Symposium for Computational Neuroscience, Oct 1--3, Berlin, Germany}, publisher = {Bernstein Center for Computational Neuroscience (BCCN) Berlin}, year = {2006}, pages = {67} }
Sprekeler, H. & Wiskott, L.	2007	Spike-timing-dependent plasticity and temporal input statistics. [BibTeX] [URL]	Proc. 16^th Annual Computational Neuroscience Meeting (CNS'06), Jul 7-12, Toronto, Canada .	inproceedings
BibTeX: @inproceedings{SprekelerWiskott-2007, author = {H. Sprekeler and L. Wiskott}, title = {Spike-timing-dependent plasticity and temporal input statistics.}, booktitle = {Proc.\ 16\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'06), Jul 7--12, Toronto, Canada}, year = {2007}, url = {http://www.biomedcentral.com/1471-2202/8/S2/P86}, doi = {http://doi.org/10.1186/1471-2202/8/S2/P86} }
Sprekeler, H. & Wiskott, L.	2008	Understanding slow feature analysis: a mathematical framework [Abstract] [BibTeX] [URL]	Cognitive Sciences EPrint Archive (CogPrints) , 6223.	misc
Abstract: Slow feature analysis is an algorithm for unsupervised learning of invariant representations from data with temporal correlations. Here, we present a mathematical analysis of slow feature analysis for the case where the input-output functions are not restricted in complexity. We show that the optimal functions obey a partial differential eigenvalue problem of a type that is common in theoretical physics. This analogy allows the transfer of mathematical techniques and intuitions from physics to concrete applications of slow feature analysis, thereby providing the means for analytical predictions and a better understanding of simulation results. We put particular emphasis on the situation where the input data are generated from a set of statistically independent sources. The dependence of the optimal functions on the sources is calculated analytically for the cases where the sources have Gaussian or uniform distribution.
BibTeX: @misc{SprekelerWiskott-2008, author = {Henning Sprekeler and Laurenz Wiskott}, title = {Understanding slow feature analysis: a mathematical framework}, year = {2008}, volume = {6223}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/6223/} }
Sprekeler, H. & Wiskott, L.	2011	A theory of slow feature analysis for transformation-based input signals with an application to complex cells [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 23(2), 303-335. Publ. MIT Press - Journals.	article
Abstract: We develop a group-theoretical analysis of slow feature analysis for the case where the input data are generated by applying a set of continuous transformations to static templates. As an application of the theory, we analytically derive nonlinear visual receptive fields and show that their optimal stimuli, as well as the orientation and frequency tuning, are in good agreement with previous simulations of complex cells in primary visual cortex (Berkes and Wiskott, 2005). The theory suggests that side and end stopping can be interpreted as a weak breaking of translation invariance. Direction selectivity is also discussed.
BibTeX: @article{SprekelerWiskott-2011, author = {Henning Sprekeler and Laurenz Wiskott}, title = {A theory of slow feature analysis for transformation-based input signals with an application to complex cells}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2011}, volume = {23}, number = {2}, pages = {303--335}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00072}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/SprekelerWiskott-2011-NeurComp-SFATheoryRFs.pdf}, doi = {http://doi.org/10.1162/NECO_a_00072} }
Sprekeler, H.; Zito, T. & Wiskott, L.	2010	An extension of slow feature analysis for nonlinear blind source separation. [Abstract] [BibTeX] [URL] [URL(2)]	Cognitive Sciences EPrint Archive (CogPrints) , 7056.	misc
Abstract: We present and test an extension of slow feature analysis as a novel approach to nonlinear blind source separation. The algorithm relies on temporal correlations and iteratively reconstructs a set of statistically independent sources from arbitrary nonlinear instantaneous mixtures. Simulations show that it is able to invert a complicated nonlinear mixture of two audio signals with a reliability of more than 90%. The algorithm is based on a mathematical analysis of slow feature analysis for the case of input data that are generated from statistically independent sources.
BibTeX: @misc{SprekelerZitoEtAl-2010, author = {Henning Sprekeler and Tiziano Zito and Laurenz Wiskott}, title = {An extension of slow feature analysis for nonlinear blind source separation.}, year = {2010}, volume = {7056}, howpublished = {Cognitive Sciences EPrint Archive (CogPrints)}, url = {http://cogprints.org/7056/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/SprekelerZitoEtAl-2010-CogPrints-xSFA.pdf} }
Sprekeler, H.; Zito, T. & Wiskott, L.	2014	An extension of slow feature analysis for nonlinear blind source separation [Abstract] [BibTeX] [URL] [URL(2)]	Journal of Machine Learning Research , 15, 921-947.	article
Abstract: We present and test an extension of slow feature analysis as a novel approach to nonlinear blind source separation. The algorithm relies on temporal correlations and iteratively reconstructs a set of statistically independent sources from arbitrary nonlinear instantaneous mixtures. Simulations show that it is able to invert a complicated nonlinear mixture of two audio signals with a high reliability. The algorithm is based on a mathematical analysis of slow feature analysis for the case of input data that are generated from statistically independent sources.
BibTeX: @article{SprekelerZitoEtAl-2014, author = {Henning Sprekeler and Tiziano Zito and Laurenz Wiskott}, title = {An extension of slow feature analysis for nonlinear blind source separation}, journal = {Journal of Machine Learning Research}, year = {2014}, volume = {15}, pages = {921--947}, url = {http://jmlr.org/papers/v15/sprekeler14a.html}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/SprekelerZitoEtAl-2014-JMLR-xSFA.pdf} }
Sun, H.; Fu, X.; Zhong, S. & Wang, L.	2020	Mixed-kernel Slow Feature Analysis Based Feature Extraction on Civil Aero-engine gas path parameters [Abstract] [BibTeX] [URL]	2020 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) , 234-241.	inproceedings
Abstract: A mixed-kernel Slow Feature Analysis (MKSFA) based feature extraction on civil aero-engine gas path parameters is proposed to extract the slowest time-varying features of gas path parameters on civil aero-engine. By introducing the mixed-kernel function in Slow Feature Analysis, the original input data can be fully expanded into a high-dimensional feature space while avoiding the computational difficulties caused by the high-dimensional feature space. The result of MKSFA is compared with the traditional feature extraction of principal component analysis and auto-encoder to verify the reliability of this algorithm, which proves that the feature extraction method proposed in this paper is more suitable for the anomaly detection field of aero-engine gas path parameters.
BibTeX: @inproceedings{9353168, author = {Sun, Hao and Fu, Xuyun and Zhong, Shisheng and Wang, Lijun}, title = {Mixed-kernel Slow Feature Analysis Based Feature Extraction on Civil Aero-engine gas path parameters}, booktitle = {2020 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)}, year = {2020}, pages = {234-241}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9353168}, doi = {http://doi.org/10.1109/SDPC49476.2020.9353168} }
Sun, L.; Jia, K.; Chan, T.-H.; Fang, Y.; Wang, G. & Yan, S.	2014	DL-SFA: deeply-learned slow feature analysis for action recognition [Abstract] [BibTeX] [URL] [URL(2)]	Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2625-2632.	inproceedings
Abstract: Most of the previous work on video action recognition use complex hand-designed local features, such as SIFT, HOG and SURF, but these approaches are implemented sophisticatedly and difficult to be extended to other sensor modalities. Recent studies discover that there are no universally best hand-engineered features for all datasets, and learning features directly from the data may be more advantageous. One such endeavor is Slow Feature Analysis (SFA) proposed by Wiskott and Sejnowski [33]. SFA can learn the invariant and slowly varying features from input signals and has been proved to be valuable in human action recognition [34]. It is also observed that the multi-layer feature representation has succeeded remarkably in widespread machine learning applications. In this paper, we propose to combine SFA with deep learning techniques to learn hierarchical representations from the video data itself. Specifically, we use a two-layered SFA learning structure with 3D convolution and max pooling operations to scale up the method to large inputs and capture abstract and structural features from the video. Thus, the proposed method is suitable for action recognition. At the same time, sharing the same merits of deep learning, the proposed method is generic and fully automated. Our classification results on Hollywood2, KTH and UCF Sports are competitive with previously published results. To highlight some, on the KTH dataset, our recognition rate shows approximately 1% improvement in comparison to state-of-the-art methods even without supervision or dense sampling.
BibTeX: @inproceedings{SunJiaEtAl-2014, author = {Sun, Lin and Jia, Kui and Chan, Tsung-Han and Fang, Yuqiang and Wang, Gang and Yan, Shuicheng}, title = {{DL-SFA}: deeply-learned slow feature analysis for action recognition}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year = {2014}, pages = {2625--2632}, url = {http://ieeexplore.ieee.org/document/6909732/?arnumber=6909732}, url2 = {https://pdfs.semanticscholar.org/45a6/8cc80f3f30759192daba83418101edd84ccf.pdf}, doi = {http://doi.org/10.1109/cvpr.2014.336} }
Tao, R. & Li, B.	2015	SAR automatic target recognition based on slow feature analysis [Abstract] [BibTeX] [URL]	Conference on Progress in Informatics and Computing (PIC), 2015 IEEE International , 40-45.	inproceedings
Abstract: This paper presents a new Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) method based on slow feature analysis. Slow feature analysis (SFA) is a method for learning invariant or slowly varying features from multi-dimensional input signal. The SFA-based SAR ATR system does not require any pre-processing, such as filtering or pose estimation of the image. The performance of the method is evaluated via three classification experiments on Moving and Stationary Target Acquisition and Recognition (MSTAR) database. The experiment results show the effectiveness of the proposed method on SAR ATR problem.
BibTeX: @inproceedings{TaoLi-2015, author = {Tao, Rentuo and Li, Bin}, title = {{SAR} automatic target recognition based on slow feature analysis}, booktitle = {Conference on Progress in Informatics and Computing (PIC), 2015 IEEE International}, year = {2015}, pages = {40--45}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7489806}, doi = {http://doi.org/10.1109/pic.2015.7489806} }
Teichmann, M.; Wiltschut, J. & Hamker, F.	2012	Learning invariance from natural images inspired by observations in the primary visual cortex [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 24(5), 1271-1296. Publ. MIT Press.	article
Abstract: The human visual system has the remarkable ability to largely recognize objects invariant of their position, rotation, and scale. A good interpretation of neurobiological findings involves a computational model that simulates signal processing of the visual cortex. In part, this is likely achieved step by step from early to late areas of visual perception. While several algorithms have been proposed for learning feature detectors, only few studies at hand cover the issue of biologically plausible learning of such invariance. In this study, a set of Hebbian learning rules based on calcium dynamics and homeostatic regulations of single neurons is proposed. Their performance is verified within a simple model of the primary visual cortex to learn so-called complex cells, based on a sequence of static images. As a result, the learned complex-cell responses are largely invariant to phase and position.
BibTeX: @article{TeichmannWiltschutEtAl-2012, author = {Teichmann, Michael and Wiltschut, Jan and Hamker, Fred}, title = {Learning invariance from natural images inspired by observations in the primary visual cortex}, journal = {Neural Computation}, publisher = {MIT Press}, year = {2012}, volume = {24}, number = {5}, pages = {1271--1296}, url = {http://www.mitpressjournals.org/doi/10.1162/NECO_a_00268}, url2 = {https://www.researchgate.net/profile/Fred_Hamker/publication/232701445_Learning_invariance_in_visual_perception/links/0fcfd510253bc02684000000.pdf}, doi = {http://doi.org/10.1162/neco_a_00268} }
Tewari, A.; Taetz, B. & Grandidier, F.	2015	Using mutual independence of slow features for improved information extraction and better hand-pose classification [BibTeX] [URL(2)]	Journal of WSCG . Publ. Václav Skala-UNION Agency.	article
BibTeX: @article{TewariTaetzEtAl-2015, author = {Tewari, Aditya and Taetz, Bertram and Grandidier, Fr{\'e}d{\'e}ric}, title = {Using mutual independence of slow features for improved information extraction and better hand-pose classification}, journal = {Journal of WSCG}, publisher = {V{\'a}clav Skala-UNION Agency}, year = {2015}, url2 = {https://www.researchgate.net/profile/Bertram_Taetz2/publication/282314711_Using_mutual_independence_of_slow_features_for_improved_information_extraction_and_better_hand-pose_classification/links/5612287b08ae6b29b49e4b1c.pdf} }
Theriault, C.; Thome, N. & Cord, M.	2013	Dynamic scene classification: learning motion descriptors with slow features analysis [BibTeX]	Conference on Computer Vision and Pattern Recognition (CVPR), 2013 IEEE , 2603-2610.	inproceedings
BibTeX: @inproceedings{TheriaultThomeEtAl-2013, author = {Theriault, Christian and Thome, Nicolas and Cord, Matthieu}, title = {Dynamic scene classification: learning motion descriptors with slow features analysis}, booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR), 2013 IEEE}, year = {2013}, pages = {2603--2610} }
Thériault, C.; Thome, N.; Cord, M. & Pérez, P.	2014	Perceptual principles for video classification with slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Journal of Selected Topics in Signal Processing , 8(3), 428-437. Publ. IEEE.	article
Abstract: At the core of vision research is the notion of perceptual invariance. The question of how the visual system is able to develop stable or invariant states through the ever transforming environment is central to understanding the brain's recognition process. The coined term slowness principle used in slow feature analysis is a reference to the brain's ability to generate slow changing and thus stable percepts in response to the fast varying visual stimulations in the environment. Based on this principle this paper deals with categorization of video sequences composed of dynamic natural scenes. Unlike models relying on supervised learning or handcrafted descriptors, we represent videos using unsupervised learning of motion features. Our method is based on: 1) Slow feature analysis principle from which motion features representing the principal and more stable motion components of training videos are learned. 2) Integration of the local motion feature into a global classification architecture. Classification experiments produce 11% and 19% improvements compared to state-of-the-art methods on two dynamic natural scenes data sets. A quantitative and qualitative analysis illustrates how the learned slow features untangle the input manifolds and remain stable under various parameters settings.
BibTeX: @article{TheriaultThomeEtAl-2014, author = {Th{\'e}riault, Christian and Thome, Nicolas and Cord, Matthieu and P{\'e}rez, Patrick}, title = {Perceptual principles for video classification with slow feature analysis}, journal = {IEEE Journal of Selected Topics in Signal Processing}, publisher = {IEEE}, year = {2014}, volume = {8}, number = {3}, pages = {428--437}, url = {http://ieeexplore.ieee.org/document/6783694/}, url2 = {https://pdfs.semanticscholar.org/1099/d475ee0807fc0e4aec55b636db4abc01dcb6.pdf}, doi = {http://doi.org/10.1109/jstsp.2014.2315742} }
Tsujimoto, K. & Omori, T.	2020	Switching Probabilistic Slow Feature Analysis for Time Series Data [Abstract] [BibTeX] [URL(2)]	International Journal of Machine Learning and Computing , 10(6).	article
Abstract: Slow feature analysis (SFA) is a machine learning method for extracting slowly time-varying feature from multidimensional time series data. Recently, probabilistic SFA (PSFA) that extends SFA to a probabilistic framework has been proposed. The PSFA can be applied to stationary time series data with noise and missing values. In order to deal with nonstationary time series data including change points, we propose a switching probabilistic slow feature analysis (switching PSFA) in this paper. By introducing a switching state space model, it is possible to extract slowly varying information even when system parameters change with time. Using the proposed method, we show that slowly time-varying components can be extracted more accurately from time-series data with non-stationarity.
BibTeX: @article{tsujimoto2020switching, author = {Tsujimoto, Kazuki and Omori, Toshiaki}, title = {Switching Probabilistic Slow Feature Analysis for Time Series Data}, journal = {International Journal of Machine Learning and Computing}, year = {2020}, volume = {10}, number = {6}, url2 = {https://www.researchgate.net/profile/Toshiaki-Omori-3/publication/343600919_Switching_Probabilistic_Slow_Feature_Analysis_for_Time_Series_Data/links/5fbcbe4592851c933f51bf08/Switching-Probabilistic-Slow-Feature-Analysis-for-Time-Series-Data.pdf} }
Turner, R. & Sahani, M.	2007	A maximum-likelihood interpretation for slow feature analysis [Abstract] [BibTeX] [URL]	Neural Comput , 19(4), 1022-1038.	article
Abstract: The brain extracts useful features from a maelstrom of sensory information, and a fundamental goal of theoretical neuroscience is to work out how it does so. One proposed feature extraction strategy is motivated by the observation that the meaning of sensory data, such as the identity of a moving visual object, is often more persistent than the activation of any single sensory receptor. This notion is embodied in the slow feature analysis (SFA) algorithm, which uses "slowness" as a heuristic by which to extract semantic information from multidimensional time series. Here, we develop a probabilistic interpretation of this algorithm, showing that inference and learning in the limiting case of a suitable probabilistic model yield exactly the results of SFA. Similar equivalences have proved useful in interpreting and extending comparable algorithms such as independent component analysis. For SFA, we use the equivalent probabilistic model as a conceptual springboard with which to motivate several novel extensions to the algorithm.
BibTeX: @article{TurnerSahani-2007, author = {Turner, R. and Sahani, M.}, title = {A maximum-likelihood interpretation for slow feature analysis}, journal = {Neural Comput}, year = {2007}, volume = {19}, number = {4}, pages = {1022--1038}, url = {http://www.mitpressjournals.org/doi/10.1162/neco.2007.19.4.1022}, doi = {http://doi.org/10.1162/neco.2007.19.4.1022} }
Turner, R.E.	2010	Statistical models for natural sounds [Abstract] [BibTeX] [URL] [URL(2)]	UCL (University College London), UCL (University College London) .	phdthesis
Abstract: It is important to understand the rich structure of natural sounds in order to solve im- portant tasks, like automatic speech recognition, and to understand auditory processing in the brain. This thesis takes a step in this direction by characterising the statistics of simple natural sounds. We focus on the statistics because perception often appears to depend on them, rather than on the raw waveform. For example the perception of au- ditory textures, like running water, wind, fire and rain, depends on summary-statistics, like the rate of falling rain droplets, rather than on the exact details of the physical source. In order to analyse the statistics of sounds accurately it isnecessary to improve a number of traditional signal processing methods, including those for amplitude demod- ulation, time-frequency analysis, and sub-band demodulation. These estimation tasks are ill-posed and therefore it is natural to treat them as Bayesian inference problems. The new probabilistic versions of these methods have several advantages. For exam- ple, they perform more accurately on natural signals and aremore robust to noise, they can also fill-in missing sections of data, and provide error-bars. Furthermore, free-parameters can be learned from the signal. Using these new algorithms we demon- strate that the energy, sparsity, modulation depth and modulation time-scale in each sub-band of a signal are critical statistics, together with the dependencies between the sub-band modulators. In order to validate this claim, a model containing co-modulated coloured noise carriers is shown to be capable of generating a range of realistic sounding auditory textures. Finally, we explored the connection between the statistics of natural sounds and per- ception. We demonstrate that inference in the model for auditory textures qualitatively replicates the primitive grouping rules that listeners use to understand simple acoustic scenes. This suggests that the auditory system is optimised for the statistics of natural sounds.
BibTeX: @phdthesis{Turner-2010, author = {Turner, Richard E}, title = {Statistical models for natural sounds}, school = {UCL (University College London)}, year = {2010}, url = {http://discovery.ucl.ac.uk/19231/1/19231.pdf}, url2 = {http://www.gatsby.ucl.ac.uk/~turner/Publications/turner-2010.pdf} }
Valpola, H.	2004	Behaviourally meaningful representations from normalisation and context-guided denoising [Abstract] [BibTeX] [URL(2)]	Artificial Intelligence Laboratory, University of Zurich, Switzerland, Artificial Intelligence Laboratory, University of Zurich, Switzerland .	misc
Abstract: Many existing independent comp onent analysis algorithms include a prepro cessing stage where the inputs are sphered. This amounts to normalising the data such that all correlations between the variables are removed. In this work, I show that sphering allows very weak contextual modulation to steer the development of meaningful features. Context-biased competition has been proposed as a model of covert attention and I propose that sphering-like normalisation also allows weaker top-wn bias to guide attention.
BibTeX: @misc{Valpola-2004, author = {Valpola, Harri}, title = {Behaviourally meaningful representations from normalisation and context-guided denoising}, school = {Artificial Intelligence Laboratory, University of Zurich, Switzerland}, year = {2004}, url2 = {https://pdfs.semanticscholar.org/ac88/a7f68913895694de6f6bbf2c74e9a79fd2db.pdf} }
Valpola, H. & Särelä, J.	2004	Context-guided denoising [BibTeX] [URL(2)]	.	misc
BibTeX: @misc{ValpolaSaerelae-2004, author = {Valpola, Harri and S{\"a}rel{\"a}, Jaakko}, title = {Context-guided denoising}, year = {2004}, url2 = {http://users.ics.aalto.fi/jaakkos/Skye04/CGDposter.pdf} }
Vasudevan, A.; Muralidharan, S.; Chintapalli, S. & Raman, S.	2013	Dynamic scene classification using spatial and temporal cues [Abstract] [BibTeX] [URL] [URL(2)]	Proceedings of the IEEE International Conference on Computer Vision Workshops , 803-810.	inproceedings
Abstract: A real world scene may contain several objects with different spatial and temporal characteristics. This paper proposes a novel method for the classification of natural scenes by processing both spatial and temporal information from the video. For extracting the spatial characteristics, we build spatial pyramids using the spatial pyramid matching (SPM) algorithm on SIFT descriptors while for the motion characteristics, we introduce a five dimensional feature vector extracted from the optical flow field. We employ SPM on combined SIFT and motion feature descriptors to perform classification. We demonstrate that the proposed approach shows significant improvement in scene classification as compared to the SPM algorithm on SIFT spatial feature descriptors alone.
BibTeX: @inproceedings{VasudevanMuralidharanEtAl-2013, author = {Vasudevan, Arun and Muralidharan, Srikanth and Chintapalli, Shiva and Raman, Shanmuganathan}, title = {Dynamic scene classification using spatial and temporal cues}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops}, year = {2013}, pages = {803--810}, url = {http://ieeexplore.ieee.org/document/6755979/}, url2 = {https://pdfs.semanticscholar.org/dee6/fa0918ffbf724b2bf55845aabf8fc00e67c6.pdf}, doi = {http://doi.org/10.1109/iccvw.2013.110} }
Vollgraf, R. & Obermayer, K.	2006	Sparse optimization for second order kernel methods [Abstract] [BibTeX] [URL]	Conference on Neural Networks, 2006. IJCNN'06. International Joint , 145-152.	inproceedings
Abstract: We present a new optimization procedure which is particularly suited for the solution of second-order kernel methods like e.g. Kernel-PCA. Common to these methods is that there is a cost function to be optimized, under a positive definite quadratic constraint, which bounds the solution. For example, in kernel-PCA the constraint provides unit length and orthogonal (in feature space) principal components. The cost function is often quadratic which allows to solve the problem as a generalized eigenvalue problem. However, in contrast to support vector machines, which employ box constraints, quadratic constraints usually do not lead to sparse solutions. Here we give up the structure of the generalized eigenvalue problem in favor of a non-quadratic regularization term added to the cost function, which enforces sparse solutions. To optimize this more 'complicated' cost function, we introduce a modified conjugate gradient descent method. Starting from an admissible point, all iterations are carried out inside the subspace of admissible solutions, which is defined by the hyper-ellipsoidal constraint surface.
BibTeX: @inproceedings{VollgrafObermayer-2006, author = {Vollgraf, Roland and Obermayer, Klaus}, title = {Sparse optimization for second order kernel methods}, booktitle = {Conference on Neural Networks, 2006. IJCNN'06. International Joint}, year = {2006}, pages = {145--152}, url = {http://ieeexplore.ieee.org/document/1716083/}, doi = {http://doi.org/10.1109/ijcnn.2006.246672} }
Waegeman, T.; Schrauwen, B.; Jaeger, H. & others	2012	Technical report on hierarchical reservoir computing architectures [Abstract] [BibTeX] [URL]	Ghent University, Ghent University .	techreport
Abstract: One approach for building architectures (of which an overview was given in D.6.1) in AMARSi is to use reservoir computing. Here, untrained (or unsupervised trained) recurrent neural networks are used for motion control by learning simple readouts on the dynamic representation generated by the dynamic RNN system. Although single reservoirs are able to generate rich and tunable control patterns (as demonstrated in D.4.1), to allow composition of motion or high-level control, these modules need to be built in an architecture. An active research area in reservoir computing is to build hierarchical reservoir systems. The main reason for this is that reservoirs basically are band-pass systems and can only represent information in a limited frequency band. If information at both fast and slow timescales needs to be integrated, a natural approach is to build a hierarchical system where each layer operates at a different time scale. The big challenge in these hierarchies is how to learn intermediate representations that link the various layers, and especially how bottom-up and top-down information flows need to be organized. We believe that these hierarchical reservoir computing systems are good candidates to build (at least part of) architectures required in AMARSi for rich motor control. In this short deliverable we give an overview of and references to current approaches in hierarchical reservoir computing, several of which have been investigated on speech and handwriting recognition problems in the sister EU project ORGANIC (http://reservoir-computing.org/organic). Many of these hierarchical systems can be used to not only generate dynamical feature hierarchies, but are also able to learn a hierarchy of pattern controller, of special interest to the AMARSi project.
BibTeX: @techreport{WaegemanSchrauwenEtAl-2012, author = {Waegeman, Tim and Schrauwen, Benjamin and Jaeger, Herbert and others}, title = {Technical report on hierarchical reservoir computing architectures}, school = {Ghent University}, year = {2012}, url = {https://biblio.ugent.be/publication/3005080/file/3005088} }
Walter, W.	2005	Slow feature analysis [Abstract] [BibTeX] [URL(2)]	.	misc
Abstract: Die sogenannte Slow Feature Analysis ist eine neue Idee, aus zeitabhängigen Daten die wichtigen Komponenten herauszufinden und die redundanten Informationen zu vernachlässigen. Der Grundgedanke dabei ist, dass die Welt sich langsam verändert, während Sensoren ständig wechselnde Daten liefern.
BibTeX: @misc{Walter-2005, author = {Walter, Welf}, title = {Slow feature analysis}, year = {2005}, url2 = {http://www.informatik.uni-ulm.de/ni/Lehre/SS05/HauptseminarMustererkennung/ausarbeitungen/Walter.pdf} }
Wang, G. & Chen, X.	2015	Nonstationary time series prediction combined with slow feature analysis [Abstract] [BibTeX] [URL]	Nonlinear Processes in Geophysics , 22(4), 377-382. Publ. Copernicus GmbH.	article
Abstract: Almost all climate time series have some degree of nonstationarity due to external driving forces perturbing the observed system. Therefore, these external driving forces should be taken into account when constructing the climate dynamics. This paper presents a new technique of obtaining the driving forces of a time series from the slow feature analysis (SFA) approach, and then introduces them into a predictive model to predict nonstationary time series. The basic theory of the technique is to consider the driving forces as state variables and to incorporate them into the predictive model. Experiments using a modified logistic time series and winter ozone data in Arosa, Switzerland, were conducted to test the model. The results showed improved prediction skills.
BibTeX: @article{WangChen-2015, author = {Wang, G and Chen, X}, title = {Nonstationary time series prediction combined with slow feature analysis}, journal = {Nonlinear Processes in Geophysics}, publisher = {Copernicus GmbH}, year = {2015}, volume = {22}, number = {4}, pages = {377--382}, url = {http://www.nonlin-processes-geophys.net/22/377/2015/npg-22-377-2015.pdf}, doi = {http://doi.org/10.5194/npg-22-377-2015} }
Wang, G.; Yang, P. & Zhou, X.	2016	Extracting the driving force from ozone data using slow feature analysis [Abstract] [BibTeX] [URL]	Theoretical and Applied Climatology , 124(3-4), 985-989. Publ. Springer.	article
Abstract: Slow feature analysis (SFA) is a recommended technique for extracting slowly varying features from a quickly varying signal. In this work, we apply SFA to total ozone data from Arosa, Switzerland. The results show that the signal of volcanic eruptions can be found in the driving force, and wavelet analysis of this driving force shows that there are two main dominant scales, which may be connected with the effect of climate mode such as North Atlantic Oscillation (NAO) and solar activity. The findings of this study represent a contribution to our understanding of the causality from observed climate data.
BibTeX: @article{WangYangEtAl-2016, author = {Wang, Geli and Yang, Peicai and Zhou, Xiuji}, title = {Extracting the driving force from ozone data using slow feature analysis}, journal = {Theoretical and Applied Climatology}, publisher = {Springer}, year = {2016}, volume = {124}, number = {3-4}, pages = {985--989}, url = {http://link.springer.com/content/pdf/10.1007/s00704-015-1475-1.pdf}, doi = {http://doi.org/10.1007/s00704-015-1475-1} }
Wang, J. & Zhao, C.	2020	Variants of slow feature analysis framework for automatic detection and isolation of multiple oscillations in coupled control loops [Abstract] [BibTeX] [URL]	Computers & Chemical Engineering , 141, 107029.	article
Abstract: Oscillation is a frequent type of control performance degradation. Usually, multiple oscillations simultaneously propagate through coupled control loops, bringing challenges to detection and isolation. An automatic oscillation analytics scheme is proposed that extracts oscillations before oscillation detection and isolation. Two variants of slow feature analysis (SFA), termed multi-lag SFA and multi-lag dynamic SFA, are proposed and compared to explore the time-lag effect and multi-lag autocorrelations. A novel isolation index is proposed to reveal the attenuation trend of oscillations from the energy viewpoint. One of the main advantages is that the proposed framework incorporates an oscillation extraction by using multi-lag dynamic SFA, greatly improving the performance for oscillation detection and isolation. The proposed method is also applicable to ascertain roots and travel paths in the presence of multiple oscillations, requiring little human supervision. Moreover, the framework is easy to implement, which shows its abilities, both in simulations and real industrial data.
BibTeX: @article{WANG2020107029, author = {Jie Wang and Chunhui Zhao}, title = {Variants of slow feature analysis framework for automatic detection and isolation of multiple oscillations in coupled control loops}, journal = {Computers & Chemical Engineering}, year = {2020}, volume = {141}, pages = {107029}, url = {https://www.sciencedirect.com/science/article/pii/S0098135420302623}, doi = {http://doi.org/10.1016/j.compchemeng.2020.107029} }
Wang, J.; Zhao, C.; Fan, H. & Zheng, W.	2020	The Automatic Analytics Framework for Multiple Oscillations in the Coupled Control Loops via a New Variant of Slow Feature Analysis [Abstract] [BibTeX] [URL]	IFAC-PapersOnLine , 53(2), 11632-11637.	article
Abstract: Oscillation is a frequent type of control performance degradation in the process. Multiple oscillations may propagate in the coupled control loops, bringing challenges to detection and localization of oscillations. In this paper, a time-frequency analysis framework including detection, extraction, and localization of oscillations is proposed. The method is based on a new variant of slow feature analysis (SFA), termed multi-lag derivatives dynamic slow feature analysis (MDSFA), and a new indicator, termed oscillation matched degree (OMD). To detect and reveal the possible oscillation sources, MDSFA is proposed to extract features with different rates from the observed data and probe into the time-delay effect and multi-lag autocorrelations specific to control loops. To pinpoint the root loops and travel paths of oscillations, the OMD indicator is designed via the spectral analysis, which can measure the oscillation frequencies and amplitudes. The proposed method is verified to be able to detect and locate oscillations automatically and efficiently via the real thermal power process.
BibTeX: @article{WANG202011632, author = {Jie Wang and Chunhui Zhao and Haidong Fan and Weijian Zheng}, title = {The Automatic Analytics Framework for Multiple Oscillations in the Coupled Control Loops via a New Variant of Slow Feature Analysis}, journal = {IFAC-PapersOnLine}, year = {2020}, volume = {53}, number = {2}, pages = {11632-11637}, url = {https://www.sciencedirect.com/science/article/pii/S2405896320309526}, doi = {http://doi.org/10.1016/j.ifacol.2020.12.645} }
Wang, J.; Zhao, Z. & Liu, F.	2020	Robust Slow Feature Analysis for Statistical Process Monitoring [Abstract] [BibTeX] [URL]	Industrial & Engineering Chemistry Research , 59(27), 12504-12513.	article
Abstract: Slow feature analysis (SFA) is being adopted in the process monitoring and fault diagnosis as a new latent variable extraction and dimension reduction method. As temporally relevant dynamic features extracted by SFA, slow features (SFs) can reveal typical systematic trends. However, SFA cannot resist the influence of outliers, which can deteriorate the performance of the SFA monitoring model since SFA considers that the modeling data contain only slow features and quickly varying noise. In this study, a robust SFA (RSFA) method based on the M-estimator is proposed, based on which a robust SFA monitoring model is established. Such a method can eliminate the steady and dynamic anomalies due to outliers while obtaining a precise estimation of normalization factors. It properly detects outliers in the eigendecomposition and replaces them with suitable values. Finally, the feasibility and effectiveness of the RSFA monitoring method are demonstrated by a numerical simulation and Tennessee Eastman (TE) benchmark process.
BibTeX: @article{doi:10.1021/acs.iecr.0c01512, author = {Wang, Jiafeng and Zhao, Zhonggai and Liu, Fei}, title = {Robust Slow Feature Analysis for Statistical Process Monitoring}, journal = {Industrial \& Engineering Chemistry Research}, year = {2020}, volume = {59}, number = {27}, pages = {12504-12513}, url = {https://doi.org/10.1021/acs.iecr.0c01512}, doi = {http://doi.org/10.1021/acs.iecr.0c01512} }
Wang, K.; Chang, P. & Meng, F.	2021	Monitoring of Wastewater Treatment Process Based on Slow Feature Analysis Variational Autoencoder [Abstract] [BibTeX] [URL]	2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS) , 495-502.	inproceedings
Abstract: The wastewater treatment process (WWTP) is a complex nonlinear, uncertain and dynamic physical and biochemical reaction process. The non-linearity, uncertainty and dynamicity of the WWTP increase the difficulty of extracting data features, and also make it difficult to monitor the faults in this process. Aiming at the problems of non-linearity, uncertainty and dynamicity, a slow feature variational autoencoder (SFAVAE) process monitoring model is proposed. With the dynamicity of WWTP data taken into account, the slow feature analysis algorithm (SFA) is used to extract the slowly changing dynamic features of wastewater data. The variational autoencoder can impose Gaussian distribution restrictions on its hidden layer features, so that it can simultaneously learn nonlinear and certain features that obey the Gaussian distribution to deal with the nonlinearity and uncertainty of data. Finally, the hidden layer space of the variational autoencoder model is used to construct hidden layer feature statistics Z2 to realize process monitoring. Compared with the principal component analysis (PCA), independent component analysis (ICA), kernel principal analysis (KPCA) and variational auto-encoder (VAE) models, the experimental results of the benchmark simulation model 1 (BSM1) model show that the SFAVAE model has higher effectiveness in process monitoring.
BibTeX: @inproceedings{9455562, author = {Wang, Kai and Chang, Peng and Meng, Fanchao}, title = {Monitoring of Wastewater Treatment Process Based on Slow Feature Analysis Variational Autoencoder}, booktitle = {2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)}, year = {2021}, pages = {495-502}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9455562}, doi = {http://doi.org/10.1109/DDCLS52934.2021.9455562} }
Wang, K.; Zhang, Z. & Wang, L.	2012	Violence video detection by discriminative slow feature analysis [Abstract] [BibTeX] [URL]	Pattern Recognition , Communications in Computer and Information Science , 321, 137-144. Eds. Liu, C.-L.; Zhang, C. & Wang, L. Publ. Springer Berlin Heidelberg.	incollection
Abstract: Nowadays, Internet makes it easy for us to share all kinds of information. However, violent content in web has harmful influence on those who lack proper judgment, especially teenagers. This paper presents an approach for detecting violence in videos, where Discriminative Slow Feature Analysis (D-SFA) is introduced to learn slow feature functions from dense trajectories derived from videos. Afterwards, with the learnt slow feature functions, the Accumulated Squared Derivative (ASD) features are extracted to represent videos. Finally, a linear support vector machine (SVM) is trained for classification. We also construct a Violence Video (VV) dataset which includes 200 violence samples and 200 non-violence samples collected from Internet and movies. The experimental results on the newly established dataset demonstrate the effectiveness of the proposed method.
BibTeX: @incollection{WangZhangEtAl-2012, author = {Wang, Kaiye and Zhang, Zhang and Wang, Liang}, title = {Violence video detection by discriminative slow feature analysis}, booktitle = {Pattern Recognition}, publisher = {Springer Berlin Heidelberg}, year = {2012}, volume = {321}, pages = {137--144}, url = {http://link.springer.com/chapter/10.1007/978-3-642-33506-8_18}, doi = {http://doi.org/10.1007/978-3-642-33506-8_18} }
Wang, P.F.; Xiao, G.Q. & Tang, X.Q.	2015	Human action recognition based on fusion of slow features [BibTeX] [URL]	Multimedia, Communication and Computing Application: Proceedings of the 2014 International Conference on Multimedia, Communication and Computing Application (MCCA 2014), Xiamen, China, October 16-17, 2014 , 251.	inproceedings
BibTeX: @inproceedings{WangXiaoEtAl-2015, author = {Wang, PF and Xiao, GQ and Tang, XQ}, title = {Human action recognition based on fusion of slow features}, booktitle = {Multimedia, Communication and Computing Application: Proceedings of the 2014 International Conference on Multimedia, Communication and Computing Application (MCCA 2014), Xiamen, China, October 16-17, 2014}, year = {2015}, pages = {251}, url = {http://www.crcnetbase.com/doi/10.1201/b18512-53}, doi = {http://doi.org/10.1201/b18512-53} }
Wang, Y.; Peng, L. & Zhe, F.	2018	Face recognition using slow feature analysis and contourlet transform [BibTeX]	AIP Conference Proceedings , 1955(1), 040155.	inproceedings
BibTeX: @inproceedings{WangPengEtAl-2018, author = {Wang, Yuehao and Peng, Lingling and Zhe, Fuchuan}, title = {Face recognition using slow feature analysis and contourlet transform}, booktitle = {AIP Conference Proceedings}, year = {2018}, volume = {1955}, number = {1}, pages = {040155}, doi = {http://doi.org/10.1063/1.5033819} }
Wang, Z.; Lyu, S.; Schalk, G. & Ji, Q.	2013	Deep feature learning using target priors with applications in ECoG signal decoding for BCI. [Abstract] [BibTeX] [URL]	IJCAI .	inproceedings
Abstract: Recent years have seen a great interest in using deep architectures for feature learning from data. One drawback of the commonly used unsupervised deep feature learning methods is that for super- vised or semi-supervised learning tasks, the infor- mation in the target variables are not used until the final stage when the classifier or regressor is trained on the learned features. This could lead to over-generalized features that are not competitive on the specific supervised or semi-supervised learn- ing tasks. In this work, we describe a new learn- ing method that combines deep feature learning on mixed labeled and unlabeled data sets. Specif- ically, we describe a weakly supervised learning method of a prior supervised convolutional stacked auto-encoders (PCSA), of which information in the target variables is represented probabilistically us- ing a Gaussian Bernoulli restricted Boltzmann ma- chine (RBM). We apply this method to the decod- ing problem of an ECoG based Brain Computer Interface (BCI) system. Our experimental results show that PCSA achieves significant improvement in decoding performance on benchmark data sets compared to the unsupervised feature learning as well as to the current state-of-the-art algorithms that are based on manually crafted features.
BibTeX: @inproceedings{WangLyuEtAl-2013, author = {Wang, Zuoguan and Lyu, Siwei and Schalk, Gerwin and Ji, Qiang}, title = {Deep feature learning using target priors with applications in {ECoG} signal decoding for {BCI}.}, booktitle = {IJCAI}, year = {2013}, url = {https://pdfs.semanticscholar.org/6e67/35e290216cc5f294fe76e9211e5263e7a7fd.pdf} }
Weghenkel, B. & Wiskott, L.	2018	Slowness as a Proxy for Temporal Predictability: An Empirical Comparison [BibTeX]	Neural Computation , 30, 1151-1179.	article
BibTeX: @article{WeghenkelWiskott-2018, author = {Bj{\"o}rn Weghenkel and Laurenz Wiskott}, title = {Slowness as a Proxy for Temporal Predictability: An Empirical Comparison}, journal = {Neural Computation}, year = {2018}, volume = {30}, pages = {1151-1179}, doi = {http://doi.org/10.1162/neco_a_01070} }
Wilbert, N.	2012	Hierarchical slow feature analysis on visual stimuli and top-down reconstruction [Abstract] [BibTeX] [URL] [URL(2)]	PhD thesis, Institute for Biology, Humboldt University Berlin, D-10099 Berlin, Germany .	phdthesis
Abstract: In dieser Dissertation wird ein Modell des visuellen Systems untersucht, basierend auf dem Prinzip des unüberwachten Langsamkeitslernens und des SFA-Algorithmus (Slow Feature Analysis). Dieses Modell wird hier für die invariante Objekterkennung und verwandte Probleme eingesetzt. Das Modell kann dabei sowohl die zu Grunde liegenden diskreten Variablen der Stimuli extrahieren (z.B. die Identität des gezeigten Objektes) als auch kontinuierliche Variablen (z.B. Position und Rotationswinkel). Dabei ist es in der Lage, mit komplizierten Transformationen umzugehen, wie beispielsweise Tiefenrotation. Die Leistungsfähigkeit des Modells wird zunächst mit Hilfe von überwachten Methoden zur Datenanalyse untersucht. Anschließend wird gezeigt, dass auch die biologisch fundierte Methode des Verstärkenden Lernens (reinforcement learning) die Ausgabedaten unseres Modells erfolgreich verwenden kann. Dies erlaubt die Anwendung des Verstärkenden Lernens auf hochdimensionale visuelle Stimuli. Im zweiten Teil der Arbeit wird versucht, das hierarchische Modell mit Top-down Prozessen zu erweitern, speziell für die Rekonstruktion von visuellen Stimuli. Dabei setzen wir die Methode der Vektorquantisierung ein und verbinden diese mit einem Verfahren zum Gradientenabstieg. Die wesentlichen Komponenten der für unsere Simulationen entwickelten Software wurden in eine quelloffene Programmbibliothek integriert, in das ``Modular toolkit for Data Processing'''' (MDP). Diese Programmkomponenten werden im letzten Teil der Dissertation vorgestellt.
BibTeX: @phdthesis{Wilbert-2012, author = {Niko Wilbert}, title = {Hierarchical slow feature analysis on visual stimuli and top-down reconstruction}, school = {Institute for Biology}, year = {2012}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?id=39426}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Wilbert-2012-PhDThesis.pdf} }
Wilbert, N.; Legenstein, R.; Franzius, M. & Wiskott, L.	2009	Reinforcement learning on complex visual stimuli. [Abstract] [BibTeX] [URL] [URL(2)]	Proc. 18^th Annual Computational Neuroscience Meeting (CNS'09), Jul 18-23, Berlin, Germany .	inproceedings
Abstract: Animals are confronted with the problem of initiating motor actions based on very complex sensory input. We have built a biologically plausible model that uses rein- forcement learning on complex visual stimuli to direct an agent towards a target. This is made possible by first extracting a high-level representation of the scene with a hierarchical network and then applying a correlation based RL-learning rule. The sensory input given to the model consists of grayscale images of size 155 × 155 pixels; see figure. Given this com- plex input, the model should extract the position and direction of the agent, and the position of the target. This estimation is successfully performed by a multi-layer hier- archical network modeled after the visual system [1]. In each layer, we use Slow Feature Analysis (SFA) [2,3] to efficiently extract higher-level features based on time structure. SFA has the advantage that learning is done unsupervised, just by feeding the model with image sequences. The high-level output of the hierarchical net- work is then used to learn corresponding motor com- mands with a reinforcement-learning algorithm. The reward signal is given by the distance to the target, which is the only supervision signal in the whole model (biolog- ically it could be interpreted as a scent of the target). The motor command output is then used to update the scene, so the model runs in a feedback loop. The resulting trajec- tories (Figure 1) show how the model directs the agent towards its target. Our model demonstrates that by a divi- sion-of-labor strategy simple learning rules can solve a rather difficult problem.
BibTeX: @inproceedings{WilbertLegensteinEtAl-2009, author = {Niko Wilbert and Robert Legenstein and Mathias Franzius and Laurenz Wiskott}, title = {Reinforcement learning on complex visual stimuli.}, booktitle = {Proc.\ 18\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'09), Jul 18--23, Berlin, Germany}, year = {2009}, url = {http://www.biomedcentral.com/1471-2202/10/S1/P90}, url2 = {https://pdfs.semanticscholar.org/e916/f65367c0b78b2fff4320bebdd0a1618b5fef.pdf}, doi = {http://doi.org/10.1186/1471-2202-10-S1-P90} }
Wilbert, N. & Wiskott, L.	2010	Hierarchical slow feature analysis and top-down processes. [Abstract] [BibTeX] [URL] [URL(3)]	Frontiers in Computational NeuroscienceProc. Bernstein Conference on Computational Neuroscience, Sep 27-Oct 1, Berlin, Germany , 4. Publ. Frontiers Media SA.	inproceedings
Abstract: Top-down processes are thought to play an important role in the mammalian visual system, e.g., for interpreting ambiguous stimuli. Slow Feature Analysis (SFA) [2] on the other hand is proven to be an efficient algorithm for the bottom-up processing of visual stimuli [2][3]. Therefore it seems natural to combine bottom-up SFA with top-down processes. SFA is an unsupervised learning algorithm that leverages the time structure of incoming stimuli to extract higher-level features. The SFA algorithm works with continuous, real variables. The algorithm itself is linear, but can be combined with a prior expansion into a more powerful function space. Quadratic polynomials have been used successfully in hierarchical networks for the extraction of high-level features from complex visual stimuli. Unfortunately this expansion makes it difficult to relate input and output components in the layers. In particular it is generally not possible to invert the bottom-up mapping, which indicates serious obstacles for top-down processes. We explored techniques to address this inversion problem. Our methods combine gradient decent and vector quantization algorithms and allowed stimulus reconstruction at the lowest layer (see Fig. 1). The results also suggest that a further increase in reconstruction performance will require a different expansion that is partly optimized for the top-down step. [Figure] Figure 1. Stimulus reconstruction from higher-level features. (a) shows the reconstruction for a single receptive field patch on the lowest layer, with complex cell like output behavior. On the left is the original stimulus, on the right side the reconstruction, which was calculated from the layer output. In (b) the same reconstruction technique has been applied to a whole image. The first picture is the original stimulus, the second one is the reconstruction from the lowest layer output. The third image is the reconstruction from the second layer output, showing some significant reconstruction errors. References 1. Wiskott L, Sejnowski TJ: Slow feature analysis: Unsupervised learning of invariances. Neural Computation 2002; 14(4):715-770. 2. Franzius M, Sprekeler H, and Wiskott L: Slowness and sparseness lead to place, head-diretion and spatial-view cells. Public Library of Science (PLoS) Computational Biology, 3(8):e166, 2007. 3. Franzius M, Wilbert N, and Wiskott L: Invariant Object Recognition with Slow Feature Analysis. Proc. 18^th Int'l Conf. on Artificial Neural Networks, ICANN'08, Prague, Sep 3-6, eds. Vera Kurková and Roman Neruda and Jan Koutník, publ. Springer-Verlag, pp. 961-970.
BibTeX: @inproceedings{WilbertWiskott-2010, author = {N. Wilbert and L. Wiskott}, title = {Hierarchical slow feature analysis and top-down processes.}, booktitle = {Proc.\ Bernstein Conference on Computational Neuroscience, Sep 27--Oct 1, Berlin, Germany}, journal = {Frontiers in Computational Neuroscience}, publisher = {Frontiers Media {SA}}, year = {2010}, volume = {4}, url = {http://www.frontiersin.org/10.3389/conf.fncom.2010.51.00119/event_abstract}, url3 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/WilbertWiskott-2010-ProcBCCNBerlin-Poster-SFATopDown.pdf}, doi = {http://doi.org/10.3389/conf.fncom.2010.51.00119} }
Wilbert, N.; Zito, T.; Schuppner, R.-B.; Jedrzejewski-Szmek, Z.; Wiskott, L. & Berkes, P.	2013	Building extensible frameworks for data processing: the case of MDP, modular toolkit for data processing [Abstract] [BibTeX] [URL]	Journal of Computational Science , 4(5), 345-351.	article
Abstract: Data processing is a ubiquitous task in scientific research, and much energy is spent on the development of appropriate algorithms. It is thus relatively easy to find software implementations of the most common methods. On the other hand, when building concrete applications, developers are often confronted with several additional chores that need to be carried out beside the individual processing steps. These include for example training and executing a sequence of several algorithms, writing code that can be executed in parallel on several processors, or producing a visual description of the application. The Modular toolkit for Data Processing (MDP) is an open source Python library that provides an implementation of several widespread algorithms and offers a unified framework to combine them to build more complex data processing architectures. In this paper we concentrate on some of the newer features of MDP, focusing on the choices made to automatize repetitive tasks for users and developers. In particular, we describe the support for parallel computing and how this is implemented via a flexible extension mechanism. We also briefly discuss the support for algorithms that require bi-directional data flow.
BibTeX: @article{WilbertZitoEtAl-2013, author = {Niko Wilbert and Tiziano Zito and Rike-Benjamin Schuppner and Zbigniew Jedrzejewski-Szmek and Laurenz Wiskott and Pietro Berkes}, title = {Building extensible frameworks for data processing: the case of {MDP}, modular toolkit for data processing}, journal = {Journal of Computational Science}, year = {2013}, volume = {4}, number = {5}, pages = {345--351}, url = {http://www.sciencedirect.com/science/article/pii/S1877750311000913}, doi = {http://doi.org/10.1016/j.jocs.2011.10.005} }
Wiskott, L.	2013	Slow feature analysis [Abstract] [BibTeX] [URL]	Encyclopedia of Computational Neuroscience , 1-2. Eds. Jaeger, D. & Jung, R. Publ. Springer-Verlag Berlin Heidelberg.	incollection
Abstract: No abstract.
BibTeX: @incollection{Wiskott-2013, author = {Laurenz Wiskott}, title = {Slow feature analysis}, booktitle = {Encyclopedia of Computational Neuroscience}, publisher = {Springer-Verlag Berlin Heidelberg}, year = {2013}, pages = {1--2}, url = {http://link.springer.com/referenceworkentry/10.1007/978-1-4614-7320-6_682-2}, doi = {http://doi.org/10.1007/978-1-4614-7320-6_682-2} }
Wiskott, L.	2001	Unsupervised learning of invariances in a simple model of the visual system. [BibTeX]	Proc. The Mathematical, Computational and Biological Study of Vision, Nov 4-10, Oberwolfach , 21-22. Eds. Mumford, D.; Morel, J.-M. & von der Malsburg, C. Publ. Mathematisches Forschungsinstitut Oberwolfach.	inproceedings
BibTeX: @inproceedings{Wiskott-2001a, author = {Laurenz Wiskott}, title = {Unsupervised learning of invariances in a simple model of the visual system.}, booktitle = {Proc.\ The Mathematical, Computational and Biological Study of Vision, Nov 4--10, Oberwolfach}, publisher = {Mathematisches Forschungsinstitut Oberwolfach}, year = {2001}, pages = {21--22} }
Wiskott, L.	1998	Learning invariance manifolds. [BibTeX]	Proc. 8^th Intl. Conf. on Artificial Neural Networks (ICANN'98), Skövde, Sweden , Perspectives in Neural Computing , 555-560. Eds. Niklasson, L.; Bodé, M.; n & Ziemke, T. Publ. Springer, London.	inproceedings
BibTeX: @inproceedings{Wiskott-1998b, author = {Laurenz Wiskott}, title = {Learning invariance manifolds.}, booktitle = {Proc.\ 8\textsuperscript{th} Intl.\ Conf.\ on Artificial Neural Networks (ICANN'98), Sk{\"o}vde, Sweden}, publisher = {Springer}, year = {1998}, pages = {555--560} }
Wiskott, L.	1999	Unsupervised learning and generalization of translation invariance in a simple model of the visual system. [BibTeX]	Learning and Adaptivity for Connectionist Models and Neural Networks, Proc. Meeting of the GI-Working Group 1.1.2 ``Connectionism'', Sep 29, Magdeburg, Germany , 56-67. Ed. Paaß, G. Publ. GMD-Forschungszentrum Informationstechnik GmbH, Sankt Augustin.	inproceedings
BibTeX: @inproceedings{Wiskott-1999c, author = {Laurenz Wiskott}, title = {Unsupervised learning and generalization of translation invariance in a simple model of the visual system.}, booktitle = {Learning and Adaptivity for Connectionist Models and Neural Networks, Proc.\ Meeting of the GI-Working Group 1.1.2 ``Connectionism'', Sep 29, Magdeburg, Germany}, publisher = {GMD-Forschungszentrum Informationstechnik GmbH}, year = {1999}, pages = {56--67} }
Wiskott, L.	1998	Learning invariance manifolds. [BibTeX] [URL(2)]	Proc. of the 5^th Joint Symp. on Neural Computation, May 16, San Diego, CA, USA , 8, 196-203. Publ. Univ. of California, San Diego, CA.	inproceedings
BibTeX: @inproceedings{Wiskott-1998a, author = {Laurenz Wiskott}, title = {Learning invariance manifolds.}, booktitle = {Proc.\ of the 5\textsuperscript{th} Joint Symp.\ on Neural Computation, May 16, San Diego, CA, USA}, publisher = {Univ.\ of California}, year = {1998}, volume = {8}, pages = {196--203}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Wiskott-1998a-JSNC-InvarianceManifolds-Preprint.pdf} }
Wiskott, L.	1999	Learning invariance manifolds. [BibTeX]	Proc. Computational Neuroscience Meeting (CNS'98), Santa Barbara, CA, USA .	inproceedings
BibTeX: @inproceedings{Wiskott-1999b, author = {Laurenz Wiskott}, title = {Learning invariance manifolds.}, booktitle = {Proc.\ Computational Neuroscience Meeting (CNS'98), Santa Barbara, CA, USA}, year = {1999} }
Wiskott, L.	2000	Unsupervised learning of invariances in a simple model of the visual system. [BibTeX]	Proc. 9^th Annual Computational Neuroscience Meeting (CNS'00), Jul 16-20, Brugge, Belgium , 157.	inproceedings
BibTeX: @inproceedings{Wiskott-2000, author = {Laurenz Wiskott}, title = {Unsupervised learning of invariances in a simple model of the visual system.}, booktitle = {Proc.\ 9\textsuperscript{th} Annual Computational Neuroscience Meeting (CNS'00), Jul 16--20, Brugge, Belgium}, year = {2000}, pages = {157} }
Wiskott, L.	2003	Slow feature analysis: a theoretical analysis of optimal free responses. [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 15(9), 2147-2177. Publ. MIT Press - Journals.	article
Abstract: Temporal slowness is a learning principle that allows learning of invariant representations by extracting slowly varying features from quickly varying input signals. Slow feature analysis (SFA) is an efficient algorithm based on this principle, which has been applied to the learning of translation, scale, and other invariances in a simple model of the visual system. Here a theoretical analysis of the optimization problem solved by SFA is presented, which provides a deeper understanding of the simulation results obtained in previous studies.
BibTeX: @article{Wiskott-2003a, author = {Wiskott, Laurenz}, title = {Slow feature analysis: a theoretical analysis of optimal free responses.}, journal = {Neural Computation}, publisher = {{MIT} Press - Journals}, year = {2003}, volume = {15}, number = {9}, pages = {2147--2177}, url = {http://www.mitpressjournals.org/doi/10.1162/089976603322297331}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Wiskott-2003a-NeurComp-SFATheoryFree.pdf}, doi = {http://doi.org/10.1162/089976603322297331} }
Wiskott, L.	2003	Estimating driving forces of nonstationary time series with slow feature analysis. [Abstract] [BibTeX] [URL] [URL(2)]	e-print arXiv:cond-mat/0312317 .	misc
Abstract: Slow feature analysis (SFA) is a new technique for extracting slowly varying features from a quickly varying signal. It is shown here that SFA can be applied to nonstationary time series to estimate a single underlying driving force with high accuracy up to a constant offset and a factor. Examples with a tent map and a logistic map illustrate the performance.
BibTeX: @misc{Wiskott-2003b, author = {Laurenz Wiskott}, title = {Estimating driving forces of nonstationary time series with slow feature analysis.}, year = {2003}, howpublished = {e-print arXiv:cond-mat/0312317}, url = {https://arxiv.org/abs/cond-mat/0312317/}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Wiskott-2003b-arXiv-SFA-Application.pdf} }
Wiskott, L.	2006	Is slowness a learning principle of visual cortex? [BibTeX]	Proc. Japan-Germany Symposium on Computational Neuroscience, Feb 1-4, Wako, Saitama, Japan , 25. Publ. RIKEN Brain Science Institute.	inproceedings
BibTeX: @inproceedings{Wiskott-2006a, author = {Laurenz Wiskott}, title = {Is slowness a learning principle of visual cortex?}, booktitle = {Proc.\ Japan-Germany Symposium on Computational Neuroscience, Feb 1-4, Wako, Saitama, Japan}, publisher = {RIKEN Brain Science Institute}, year = {2006}, pages = {25} }
Wiskott, L. & Berkes, P.	2002	Is slowness a principle for the emergence of complex cells in primary visual cortex? [BibTeX]	Proc. Berlin Neuroscience Forum, Apr 18-20, Liebenwalde, Germany , 43. Ed. Kettenmann, H. Publ. Max-Delbrück-Centrum für Molekulare Medizin (MDC), Berlin.	inproceedings
BibTeX: @inproceedings{WiskottBerkes-2002, author = {Laurenz Wiskott and Pietro Berkes}, title = {Is slowness a principle for the emergence of complex cells in primary visual cortex?}, booktitle = {Proc.\ Berlin Neuroscience Forum, Apr 18-20, Liebenwalde, Germany}, publisher = {Max-Delbr{\"u}ck-Centrum f{\"u}r Molekulare Medizin (MDC)}, year = {2002}, pages = {43} }
Wiskott, L. & Berkes, P.	2003	Is slowness a learning principle of the visual cortex? [Abstract] [BibTeX] [URL]	ZoologyProc. Jahrestagung der Deutschen Zoologischen Gesellschaft, Jun 9-13, Berlin, Germany , 106(4), 373-382. Publ. Elsevier BV.	inproceedings
Abstract: Slow feature analysis is an algorithm for extracting slowly varying features from a quickly varying signal. It has been shown in network simulations on one-dimensional stimuli that visual invariances to shift and other transformations can be learned in an unsupervised fashion based on slow feature analysis. More recently, we have shown that slow feature analysis applied to image sequences generated from natural images using a range of spatial transformations results in units that share many properties with complex and hypercomplex cells of the primary visual cortex. We find cells responsive to Gabor stimuli with phase invariance, sharpened or widened orientation or frequency tuning, secondary response lobes, end-stopping, and cells selective for direction of motion. These results indicate that slowness may be an important principle of self-organization in the visual cortex.
BibTeX: @inproceedings{WiskottBerkes-2003, author = {Laurenz Wiskott and Pietro Berkes}, title = {Is slowness a learning principle of the visual cortex?}, booktitle = {Proc.\ Jahrestagung der Deutschen Zoologischen Gesellschaft, Jun 9--13, Berlin, Germany}, journal = {Zoology}, publisher = {Elsevier {BV}}, year = {2003}, volume = {106}, number = {4}, pages = {373--382}, url = {http://www.sciencedirect.com/science/article/pii/S0944200604701129?via%3Dihub}, doi = {http://doi.org/10.1078/0944-2006-00132} }
Wiskott, L.; Berkes, P.; Franzius, M.; Sprekeler, H. & Wilbert, N.	2011	Slow feature analysis. [Abstract] [BibTeX] [URL]	Scholarpedia , 6(4), 5282. Publ. Scholarpedia.	article
Abstract: Slow feature analysis (SFA) is an unsupervised learning algorithm for extracting slowly varying features from a quickly varying input signal. It has been successfully applied, e.g., to the self-organization of complex-cell receptive fields, the recognition of whole objects invariant to spatial transformations, the self-organization of place-cells, extraction of driving forces, and to nonlinear blind source separation.
BibTeX: @article{WiskottBerkesEtAl-2011, author = {Laurenz Wiskott and Pietro Berkes and Mathias Franzius and Henning Sprekeler and Niko Wilbert}, title = {Slow feature analysis.}, journal = {Scholarpedia}, publisher = {Scholarpedia}, year = {2011}, volume = {6}, number = {4}, pages = {5282}, url = {http://www.scholarpedia.org/article/Slow_feature_analysis}, doi = {http://doi.org/10.4249/scholarpedia.5282} }
Wiskott, L.; Franzius, M.; Berkes, P. & Sprekeler, H.	2007	Is slowness a learning principle of the visual system? [BibTeX]	Proc. 39^th European Brain and Behaviour Society Meeting (EBBS), Sep 15-19, Triest, Italy , 14-15. Eds. Treves, A.; Battaglini, P. P.; Chelazzi, L.; Diamond, M. & Vallortigara, G.	inproceedings
BibTeX: @inproceedings{WiskottFranziusEtAl-2007, author = {Laurenz Wiskott and Mathias Franzius and Pietro Berkes and Henning Sprekeler}, title = {Is slowness a learning principle of the visual system?}, booktitle = {Proc.\ 39\textsuperscript{th} European Brain and Behaviour Society Meeting (EBBS), Sep 15--19, Triest, Italy}, year = {2007}, pages = {14--15} }
Wiskott, L.; Franzius, M.; Sprekeler, H. & Appleby, P.	2009	Self-organization of place cells with slowness, sparseness, and neurogenesis. [BibTeX] [URL]	Proc. 41^st European Brain and Behaviour Society Meeting (EBBS), Sep 13-18, Rhodes Island, Greece .	inproceedings
BibTeX: @inproceedings{WiskottFranziusEtAl-2009, author = {Laurenz Wiskott and Mathias Franzius and Henning Sprekeler and Peter Appleby}, title = {Self-organization of place cells with slowness, sparseness, and neurogenesis.}, booktitle = {Proc.\ 41\textsuperscript{st} European Brain and Behaviour Society Meeting (EBBS), Sep 13--18, Rhodes Island, Greece}, year = {2009}, url = {http://www.frontiersin.org/10.3389/conf.neuro.08.2009.09.062/event_abstract}, doi = {http://doi.org/10.3389/conf.neuro.08.2009.09.062} }
Wiskott, L.; Quang, M.H.; Sprekeler, H. & Zito, T.	2010	Slow feature analysis: analyzing signals with the slowness principle. [BibTeX]	Proc. 2^nd joint Statistical Meeting Deutsche Arbeitsgemeinschaft Statistik (DAGStat'10), Mar 23-26, Dortmund, Germany , 398. Publ. Technische Universität Dortmund.	inproceedings
BibTeX: @inproceedings{WiskottQuangEtAl-2010, author = {Laurenz Wiskott and Minh Ha Quang and Henning Sprekeler and Tiziano Zito}, title = {Slow feature analysis: analyzing signals with the slowness principle.}, booktitle = {Proc.\ 2\textsuperscript{nd} joint Statistical Meeting Deutsche Arbeitsgemeinschaft Statistik (DAGStat'10), Mar 23--26, Dortmund, Germany}, publisher = {Technische Universit{\"a}t Dortmund}, year = {2010}, pages = {398} }
Wiskott, L. & Sejnowski, T.	2002	Slow feature analysis: unsupervised learning of invariances. [Abstract] [BibTeX] [URL] [URL(2)]	Neural Computation , 14(4), 715-770.	article
Abstract: Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. SFA is based on a non-linear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high dimensional input signals and to extract complex features. Slow feature analysis is applied first to complex cell tuning properties based on simple cell output including disparity and motion. Then, more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA-modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending only on the training stimulus. Surprisingly, only a few training objects sufficed to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades, if the network is trained to learn multiple invariances simultaneously.
BibTeX: @article{WiskottSejnowski-2002, author = {Laurenz Wiskott and Terrence Sejnowski}, title = {Slow feature analysis: unsupervised learning of invariances.}, journal = {Neural Computation}, year = {2002}, volume = {14}, number = {4}, pages = {715--770}, url = {http://www.mitpressjournals.org/doi/10.1162/089976602317318938}, url2 = {https://www.ini.rub.de/PEOPLE/wiskott/Reprints/WiskottSejnowski-2002-NeurComp-LearningInvariances.pdf}, doi = {http://doi.org/10.1162/089976602317318938} }
Wiskott, L.; Sprekeler, H. & Berkes, P.	2007	Towards an analytical derivation of complex cell receptive field properties. [BibTeX]	Proc. 7^th Göttingen Meeting of the German Neuroscience Society, Mar 29 - Apr 1, Göttingen, Germany , S12-2.	inproceedings
BibTeX: @inproceedings{WiskottSprekelerEtAl-2007, author = {Laurenz Wiskott and Henning Sprekeler and Pietro Berkes}, title = {Towards an analytical derivation of complex cell receptive field properties.}, booktitle = {Proc.\ 7\textsuperscript{th} G\"ottingen Meeting of the German Neuroscience Society, Mar 29 -- Apr 1, G\"ottingen, Germany}, year = {2007}, pages = {S12--2} }
Wu, C.; Du, B.; Cui, X. & Zhang, L.	2017	A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion [BibTeX]	Remote Sensing of Environment , 199, 241-255. Publ. Elsevier.	article
BibTeX: @article{WuDuEtAl-2017, author = {Wu, Chen and Du, Bo and Cui, Xiaohui and Zhang, Liangpei}, title = {A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion}, journal = {Remote Sensing of Environment}, publisher = {Elsevier}, year = {2017}, volume = {199}, pages = {241--255}, doi = {http://doi.org/10.1016/j.rse.2017.07.009} }
Wu, C.; Du, B. & Zhang, L.	2013	An automatic relative radiometric correction method based on slow feature analysis [Abstract] [BibTeX] [URL]	Conference on Image and Graphics (ICIG), 2013 Seventh International , 83-88.	inproceedings
Abstract: Radiometric correction is very important for temporal remote sensing images analysis. The key of relative radiometric correction is to accurately select pseudo-invariant features (PIFs). This process should be automatic. Slow feature analysis is a new learning algorithm to extract invariant feature from input signals. It is appreciate to separate the unchanged pixels. We apply iteration process to assign high weights to unchanged pixels. After convergence, the linear function is calculated directly with all the pixels and their weights. The experiment demonstrates that our automatic relative radiometric correction method can get a good performance.
BibTeX: @inproceedings{WuDuEtAl-2013, author = {Wu, Chen and Du, Bo and Zhang, Liangpei}, title = {An automatic relative radiometric correction method based on slow feature analysis}, booktitle = {Conference on Image and Graphics (ICIG), 2013 Seventh International}, year = {2013}, pages = {83--88}, url = {http://ieeexplore.ieee.org/abstract/document/6643642/}, doi = {http://doi.org/10.1109/icig.2013.23} }
Wu, C.; Du, B. & Zhang, L.	2014	Slow feature analysis for change detection in multispectral imagery [BibTeX] [URL(2)]	IEEE Transactions on Geoscience and Remote Sensing , 52(5), 2858-2874. Publ. IEEE.	article
BibTeX: @article{WuDuEtAl-2014, author = {Wu, Chen and Du, Bo and Zhang, Liangpei}, title = {Slow feature analysis for change detection in multispectral imagery}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, publisher = {IEEE}, year = {2014}, volume = {52}, number = {5}, pages = {2858--2874}, url2 = {http://www.lmars.whu.edu.cn/prof_web/zhangliangpei/rs/publication/Slow%20Feature%20Analysis%20for%20Change%20Detection.pdf} }
Wu, C.; Zhang, L. & Du, B.	2015	Hyperspectral anomaly change detection with slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	Neurocomputing , 151, Part 1, 175-187.	article
Abstract: The aim of hyperspectral anomaly change detection is to distinguish the small and anomalous changes from the non-changes and pervasive changes in the multi-temporal hyperspectral remote sensing image scene. The predictor is a very important process to produce the change residual image, in which the spectral differences of the background pixels should be minimized to make the target changes more anomalous and easily separated. Feature extraction is also needed for the residual image, to improve the performance. In this paper, we propose a new hyperspectral anomaly change detection method with slow feature analysis (SFA). SFA\ is first employed to obtain the change residuals. Several of the top bands of the residual image are then selected as the input of the RX\ anomaly detection algorithm to detect the anomalous changes. Two sets of experiments using multi-temporal Hyperion imagery prove that the proposed method performs better in detecting anomalous changes than the other state-of-the-art methods.
BibTeX: @article{WuZhangEtAl-2015, author = {Chen Wu and Liangpei Zhang and Bo Du}, title = {Hyperspectral anomaly change detection with slow feature analysis}, journal = {Neurocomputing}, year = {2015}, volume = {151, Part 1}, pages = {175--187}, url = {http://www.sciencedirect.com/science/article/pii/S0925231214012740}, url2 = {http://www.lmars.whu.edu.cn/prof_web/zhangliangpei/rs/publication/Hyperspectral%20Anomaly%20Change%20Detection%20with%20Slow%20Feature%20Analysis%20(2).pdf}, doi = {http://doi.org/10.1016/j.neucom.2014.09.058} }
Wu, C.; Zhang, L. & Du, B.	2017	Kernel Slow Feature Analysis for Scene Change Detection [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Geoscience and Remote Sensing , 55(4), 2367-2384.	article
Abstract: Scene change detection between multitemporal image scenes can be used to interpret the variation of regional land use, and has significant potential in the application of urban development monitoring at the semantic level. The traditional methods directly comparing the independent semantic classes neglect the temporal correlation, and thus suffer from accumulated classification errors. In this paper, we propose a novel scene change detection method via kernel slow feature analysis (KSFA) and postclassification fusion, which integrates independent scene classification with scene change detection to accurately determine scene changes and identify the “from-to” transition type. After representation with the bag-of-visual-words model, KSFA is proposed to extract the nonlinear temporally invariant features, to better measure the change probability between corresponding multitemporal image scenes. Two postclassification fusion methods, which are based on Bayesian theory and predefined rules, respectively, are then employed to identify the optimal coupled class combinations of multitemporal scene pairs. Furthermore, in addition to identifying semantic changes, the proposed method can also improve the performance of scene classification, since the unchanged scenes are more likely to belong to the same class. Two experiments with high-resolution remote sensing image scene data sets confirm that the proposed method can increase the accuracy of scene change detection, scene transition identification, and scene classification.
BibTeX: @article{7817860, author = {Wu, Chen and Zhang, Liangpei and Du, Bo}, title = {Kernel Slow Feature Analysis for Scene Change Detection}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, year = {2017}, volume = {55}, number = {4}, pages = {2367-2384}, url = {https://ieeexplore.ieee.org/document/7817860}, url2 = {https://www.semanticscholar.org/paper/Kernel-Slow-Feature-Analysis-for-Scene-Change-Wu-Zhang/fd4a4539c9b266030afaed534834ea589ee1953f}, doi = {http://doi.org/10.1109/TGRS.2016.2642125} }
Wu, C.; Zhang, L. & Du, B.	2017	Kernel Slow Feature Analysis for Scene Change Detection [BibTeX]	IEEE Transactions on Geoscience and Remote Sensing , 55(4), 2367-2384. Publ. IEEE.	article
BibTeX: @article{WuZhangEtAl-2017, author = {Chen Wu and Liangpei Zhang and Bo Du}, title = {Kernel Slow Feature Analysis for Scene Change Detection}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, publisher = {IEEE}, year = {2017}, volume = {55}, number = {4}, pages = {2367-2384} }
Wu, Y.; Wang, Z.; Xu, X.; Gong, S.; Liu, Q. & Liu, C.	2015	Spatiotemporal saliency detection using slow feature analysis and spatial information for dynamic scenes [Abstract] [BibTeX] [URL]	International Conference on Intelligent Science and Big Data Engineering , 331-340.	inproceedings
Abstract: Slow feature analysis (SFA) can extract slowly varying signals from quickly varying input data. Inspired by the temporal slowness principle, we propose a novel spatiotemporal saliency algorithm for dynamic scenes analysis. In the training phase, slow feature functions are learned from different video patches using SFA. At the stage of saliency computation, we first exploit two-layer slow feature functions to extract pixel-level high-level motion features, which represent temporal slowness of every local space-time cuboid. Temporal saliency of each location is measured by the average of the corresponding feature vector. Finally, a saliency map is generated by combining the proposed temporal saliency and existing spatial saliency. The algorithm is qualitatively and quantitatively evaluated on challenging video sequences, and achieves competitive performance in contrast to the state-of-the-art algorithm.
BibTeX: @inproceedings{WuWangEtAl-2015, author = {Wu, Yang and Wang, Zhaohui and Xu, Xin and Gong, Shengrong and Liu, Quan and Liu, Chunping}, title = {Spatiotemporal saliency detection using slow feature analysis and spatial information for dynamic scenes}, booktitle = {International Conference on Intelligent Science and Big Data Engineering}, year = {2015}, pages = {331--340}, url = {http://link.springer.com/chapter/10.1007/978-3-319-23989-7_34}, doi = {http://doi.org/10.1007/978-3-319-23989-7_34} }
Wu, Y.; Yang, Y.; Tao, C.; Li, P. & Yang, L.	2014	A study on underwater target recognition applying auditory slow feature analysis [Abstract] [BibTeX] [URL]	OCEANS 2014-TAIPEI , 1-5.	inproceedings
Abstract: Human listeners are capable of segregating and recognizing the class of signal better than machine recognizer in complex noisy conditions. In this paper, we proposed a novel approach for underwater target recognition applying auditory slow feature analysis (ASFA) based on gammatone (GT) filter and slow feature analysis. Our experimental evaluations show that the ASFA feature was proved to be considerably better than conventional acoustic features (i.e. Mel-frequency cepstral coefficients, MFCC). Moreover, the proposed ASFA feature is used for underwater target recognition system to yield promising recognition performance.
BibTeX: @inproceedings{WuYangEtAl-2014b, author = {Wu, Yaozhen and Yang, Yixin and Tao, Can and Li, Pei and Yang, Long}, title = {A study on underwater target recognition applying auditory slow feature analysis}, booktitle = {OCEANS 2014-TAIPEI}, year = {2014}, pages = {1--5}, url = {http://ieeexplore.ieee.org/document/6964334/}, doi = {http://doi.org/10.1109/oceans-taipei.2014.6964334} }
Wu, Y.; Yang, Y.; Tao, C.; Tian, F. & Yang, L.	2014	Robust underwater target recognition using auditory cepstral coefficients [Abstract] [BibTeX] [URL]	OCEANS 2014-TAIPEI , 1-4.	inproceedings
Abstract: Feature vector extraction is measured as major step in development of underwater target recognition. To improve robustness of the performance of feature vector extraction, we proposed a novel approach for robust underwater target recognition applying the auditory cepstral coefficients (ACC) based on auditory filter and cubic-log compression instead of Mel filter and logarithmic compression in Mel-frequency cepstral coefficients (MFCC). Our experimental results show that the ACC feature represents considerably better than conventional acoustic features, and the ACC feature is used for underwater target recognition system to yield promising recognition performance.
BibTeX: @inproceedings{WuYangEtAl-2014a, author = {Wu, Yaozhen and Yang, Yixin and Tao, Can and Tian, Feng and Yang, Long}, title = {Robust underwater target recognition using auditory cepstral coefficients}, booktitle = {OCEANS 2014-TAIPEI}, year = {2014}, pages = {1--4}, url = {http://ieeexplore.ieee.org/document/6964335/}, doi = {http://doi.org/10.1109/oceans-taipei.2014.6964335} }
Xia, Q.; Gao, J.-B. & Xu, C.-X.	2008	A new watermarking algorithm based on slowly feature analysis [Abstract] [BibTeX] [URL]	2008 International Conference on Apperceiving Computing and Intelligence Analysis , 70-72. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: Recently, Blind Source Separate (BSS) technique has been extended to digital watermarking field. Slowly Feature Analysis (SFA)-a kind of BSS technique-is a new unsupervised learning algorithm to learn nonlinear functions that extract slowly varying signals out of the input data. It expediently can be used to extract image feature and separate the mixed signals. Making use of the advantages of SFA, in this paper, we propose a watermarking scheme based on SFA. In the experiments, we compare our scheme with other watermarking algorithm which has been used to digital watermarking field especially wavelets. Results indicate that our scheme has not only better invisibility and good robustness to different kinds of attacks but also ease the conflicts between them.
BibTeX: @inproceedings{XiaGaoEtAl-2008, author = {Qi Xia and Jian-Bin Gao and Chun-Xiang Xu}, title = {A new watermarking algorithm based on slowly feature analysis}, booktitle = {2008 International Conference on Apperceiving Computing and Intelligence Analysis}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2008}, pages = {70--72}, url = {http://ieeexplore.ieee.org/document/4769973/}, doi = {http://doi.org/10.1109/ICACIA.2008.4769973} }
Xiao, Y. & Xia, L.	2015	Human action recognition using modified slow feature analysis and multiple kernel learning [Abstract] [BibTeX] [URL]	Multimedia Tools and Applications , 1-16. Publ. Springer.	article
Abstract: A novel human action recognition method is proposed, which includes two periods of action feature extraction and action recognition. Firstly, we use a modified slow feature analysis (SFA) to extract video local feature. Unlike slow feature analysis, we redefine the objective function with supervised information, which make the modified SFA more suitable to preserve the slow feature and label information. Meanwhile, in effort to cope with the dimension explosion in SFA, locality preserving projections (LPP) is used to reduce the quadratic expansion dimension. Secondly, we use a multiple kernel learning method (MKL) to classify human action, in which the weights of different kernels are optimized by combining Bacterial Chemotaxis method and Powell method. The results of experiments indicate the efficiency of our method.
BibTeX: @article{XiaoXia-2015, author = {Xiao, Yongliang and Xia, Limin}, title = {Human action recognition using modified slow feature analysis and multiple kernel learning}, journal = {Multimedia Tools and Applications}, publisher = {Springer}, year = {2015}, pages = {1--16}, url = {http://link.springer.com/content/pdf/10.1007/s11042-015-2569-6.pdf}, doi = {http://doi.org/10.1007/s11042-015-2569-6} }
Xiaogang, D. & Xuemin, T.	2013	Nonlinear process monitoring using dynamic kernel slow feature analysis and support vector data description [Abstract] [BibTeX] [URL]	Control and Decision Conference (CCDC), 2013 25^th Chinese , 4291-4296.	inproceedings
Abstract: For effective fault detection in nonlinear process, this paper proposed a novel nonlinear monitoring method based on dynamic kernel slow feature analysis and support vector data description (DKSFA-SVDD). SFA is a newly emerged data feature extraction technique which can find invariant features of temporally varying signals. For effective analysis on nonlinear dynamic process data, DKSFA is built which uses kernel trick to mine the nonlinear data feature and applies an augmented matrix to extract the dynamic information in measured data. In order to monitor the dynamic nonlinear data features from DKSFA, SVDD is applied to describe the distribution region of normal operation data and one monitoring index is constructed to indicate the occurrence of the abnormal event. Simulation using a continuous stirred tank reactor (CSTR) system shows that the proposed method has a good fault detection performance and outperforms the traditional KPCA method.
BibTeX: @inproceedings{XiaogangXuemin-2013, author = {Xiaogang, Deng and Xuemin, Tian}, title = {Nonlinear process monitoring using dynamic kernel slow feature analysis and support vector data description}, booktitle = {Control and Decision Conference (CCDC), 2013 25\textsuperscript{th} Chinese}, year = {2013}, pages = {4291--4296}, url = {http://ieeexplore.ieee.org/document/6561706/}, doi = {http://doi.org/10.1109/ccdc.2013.6561706} }
Xie, J.; Song, Y.; Lv, X.; Shi, H. & Song, B.	2021	Quality-related Process Monitoring of Industrial Processes based on Key Variable-Slow Feature Analysis [Abstract] [BibTeX] [URL]	2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS) , 1263-1267.	inproceedings
Abstract: In the industrial production, for the close-loop control, not all faults will affect product quality. To detect quality related fault effectively, a novel method named key variable-slow feature analysis (KV-SFA) is proposed in this work to extend the SFA algorithm to the domain of online quality-related fault detection. Firstly, key quality related process variables are selected via the combination of the least absolute shrinkage and selection operator (LASSO) method and the mechanism knowledge. Secondly, the SFA is conducted in the key variables space to extract slow features for establishing fault detection model. Then, the monitoring statistics are constructed and the control limits are estimated. Finally, the validity and effectiveness of the proposed KV-SFA method are proved through an industrial process.
BibTeX: @inproceedings{9455692, author = {Xie, Jiamin and Song, Yimeng and Lv, Xiaolong and Shi, Hongbo and Song, Bing}, title = {Quality-related Process Monitoring of Industrial Processes based on Key Variable-Slow Feature Analysis}, booktitle = {2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)}, year = {2021}, pages = {1263-1267}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=9455692}, doi = {http://doi.org/10.1109/DDCLS52934.2021.9455692} }
Xu, X. & Ding, J.	2021	Decentralized dynamic process monitoring based on manifold regularized slow feature analysis [Abstract] [BibTeX] [URL]	Journal of Process Control , 98, 79-91.	article
Abstract: For large-scale process monitoring, traditional decentralized monitoring methods fail to discriminate real faults from normal operation deviations. This paper proposes a novel decentralized method for monitoring large-scale industrial processes by exploring serial correlations and local manifold structures of the data. A block division strategy based on maximal information coefficient-spectral clustering is proposed, which can divide the measured variables into several blocks without any prior knowledge. To extract inter-block relevance, multiblock principal component analysis is introduced to whiten the original variables. On this basis, we develop a new dimensionality reduction algorithm named manifold regularized slow feature analysis (MRSFA) to capture the temporal dynamics and local structure information in each block. Monitoring statistics are constructed based on the captured feature information to concurrently monitor the operation deviations and anomalous dynamics. To achieve decision fusion, the monitoring results derived from all blocks are combined through Bayesian inference. Two case studies on the Tennessee Eastman process and a real industrial process are carried out and the experimental results demonstrate the effectiveness of the proposed method.
BibTeX: @article{XU202179, author = {Xue Xu and Jinliang Ding}, title = {Decentralized dynamic process monitoring based on manifold regularized slow feature analysis}, journal = {Journal of Process Control}, year = {2021}, volume = {98}, pages = {79-91}, url = {https://www.sciencedirect.com/science/article/pii/S0959152420303437}, doi = {http://doi.org/10.1016/j.jprocont.2020.12.006} }
Xu, Y.; Jia, M. & Mao, Z.	2021	A Novel Auto-regressive Dynamic Slow Feature Analysis Method for Dynamic chemical Process Monitoring [Abstract] [BibTeX] [URL(2)]	Chemical Engineering Science , 117236.	article
Abstract: A novel dynamic data modeling method called autoregressive dynamic slow feature analysis (RDSFA) is proposed for dynamic process concurrent monitoring of operating condition deviations and process dynamics anomalies. In this method, a multi-goal optimization question is formulized with constraints of the extract latent variable catch some variation information and mutually orthogonal to extract a group of latent features which change slowly over time and whose autoregressive model are built explicitly. When the proposed method is applied to the process monitoring, in addition to the statistics about slow feature and whose first derivatives with respect to time which have existed in SFA based monitoring frame, we add other two statistics which only contain unpredictable variability information to provide more sensitive monitoring results. Case studies on simulation data, data from a CSTR process are presented to reveal the efficiency and the superiority of the proposed method as compared to other related methods.
BibTeX: @article{XU2021117236, author = {Yuemei Xu and Mingxing Jia and Zhizhong Mao}, title = {A Novel Auto-regressive Dynamic Slow Feature Analysis Method for Dynamic chemical Process Monitoring}, journal = {Chemical Engineering Science}, year = {2021}, pages = {117236}, url2 = {https://www.sciencedirect.com/science/article/pii/S0009250921008010}, doi = {http://doi.org/10.1016/j.ces.2021.117236} }
Xv, J.; Zhang, B.; Guo, H.; Lu, J. & Lin, Y.	2019	Combining iterative slow feature analysis and deep feature learning for change detection in high-resolution remote sensing images [Abstract] [BibTeX] [URL]	Journal of Applied Remote Sensing , 13(2), 1 - 16. Publ. SPIE.	article
Abstract: In order to make full use of local neighborhood information for high-resolution remote sensing images, this study combined iterative slow feature analysis (ISFA) and stacked denoising autoencoder (SDAE) to improve the change detection precision. First, this approach introduced ISFA for initial change detection in an unsupervised way, which enlarged the separability of changed and unchanged areas. Then, by setting different membership degrees, the changed and unchanged samples were obtained through fuzzy-means clustering. Finally, the change model was built by SDAE to represent the local neighborhood features deeply, and the change detection result can be obtained after all the samples were fed into the model. Experiments were performed on three real datasets, and the results validated the effectiveness and superiority of the proposed approach.
BibTeX: @article{10.1117/1.JRS.13.024506, author = {Junfeng Xv and Baoming Zhang and Haitao Guo and Jun Lu and Yuzhun Lin}, title = {{Combining iterative slow feature analysis and deep feature learning for change detection in high-resolution remote sensing images}}, journal = {Journal of Applied Remote Sensing}, publisher = {SPIE}, year = {2019}, volume = {13}, number = {2}, pages = {1 -- 16}, url = {https://doi.org/10.1117/1.JRS.13.024506}, doi = {http://doi.org/10.1117/1.JRS.13.024506} }
Yan, S.-L.; Huo, H. & Fang, T.	2011	Image feature extraction method based on SFA and GLCM [Abstract] [BibTeX]	Computer Engineering , 37(20), 175-177.	article
Abstract: As there are still many difference between the remote sensing image from the same class,this paper proposes a new method of extracting features based on Slow Feature Analysis(SFA) and Gray Level Co-occurrence Matrix(GLCM).The image is first processed with SFA algorithm.It can eliminate the difference of the object from the same class as the biological characteristics of SFA.Then the GLCM feature is extracted from the SFA data.Results indicate that with the preprocessing of SFA,it can effectively reduce the diversity of samples from the same class and increase the distinguishability of the feature,the method is more effective and competitive than the conventional GLCM feature extraction method.
BibTeX: @article{YanHuoEtAl-2011, author = {Yan, Sheng-Li and Huo, Hong and Fang, Tao}, title = {Image feature extraction method based on {SFA} and {GLCM}}, journal = {Computer Engineering}, year = {2011}, volume = {37}, number = {20}, pages = {175--177} }
Yang, M.; Zhang, M. & Gu, Y.	2019	Two-Layer Slow Feature Analysis Network for Change Detection [Abstract] [BibTeX] [URL]	2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) , 1-4.	inproceedings
Abstract: Multi-temporal remote sensing image change detection is one of the important contents of remote sensing image processing, and has important applications in many fields. Existing multi-temporal change detection mainly deals with bi-temporal images and extracts change information by ratio or difference method. This processing cannot effectively mine the change information between multiple temporal images or time series of remote sensing images. In this paper, a two-layer slow feature analysis network (SFANet) is proposed to realize effective change detection with multiple temporal remote sensing images. The proposed method extends the existing slow feature analysis method to a two-layer network structure and forms a slow feature analysis network. On the basis of multi-temporal feature extraction in slow feature analysis network, change detection is realized by threshold method. In this paper, multi-temporal high-resolution remote sensing images are used for experiments. The experimental results demonstrate that the proposed SFANet for change detection is effective and better than several commonly used methods.
BibTeX: @inproceedings{8920976, author = {Yang, Min and Zhang, Meiling and Gu, Yanfeng}, title = {Two-Layer Slow Feature Analysis Network for Change Detection}, booktitle = {2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)}, year = {2019}, pages = {1-4}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8920976}, doi = {http://doi.org/10.1109/WHISPERS.2019.8920976} }
Yang, P.; Wang, G.; Zhang, F. & Zhou, X.	2016	Causality of global warming seen from observations: a scale analysis of driving force of the surface air temperature time series in the northern hemisphere [Abstract] [BibTeX] [URL]	Climate Dynamics , 46(9-10), 3197-3204. Publ. Springer.	article
Abstract: By using the slow feature analysis, we reconstructed the driving force for an observed monthly surface air temperature anomaly time series in the northern hemisphere. Wavelet transformation technique was then used to analyze the scale structure of the derived driving force and its causal relationship with global warming. Results showed that the driving force for the analyzed temperature climate system included two independent degrees of freedom which respectively represented the effects of 22-year solar cycle and Atlantic Multidecadal Oscillation on the climate. More importantly, the driving force is modulated in amplitude by signals with much longer time periods. The modulation controls the energy input to the climate system and its effect on the global warming is decisive. In addition, through analyzing phase transitions from zero to extremes of the modulating signals, we provide a projection for the future trend of the surface air temperature. In specific, in the next 45–65 years, the driving force will continue to rise which will drive the air temperature even warmer. This is a long term natural trend determined by the modulating amplitude signals, but not directly related to human activity.
BibTeX: @article{YangWangEtAl-2016, author = {Yang, Peicai and Wang, Geli and Zhang, Feng and Zhou, Xiuji}, title = {Causality of global warming seen from observations: a scale analysis of driving force of the surface air temperature time series in the northern hemisphere}, journal = {Climate Dynamics}, publisher = {Springer}, year = {2016}, volume = {46}, number = {9-10}, pages = {3197--3204}, url = {http://link.springer.com/article/10.1007/s00382-015-2761-4}, doi = {http://doi.org/10.1007/s00382-015-2761-4} }
Yousefi, B. & Loo, C.K.	2012	Development of fast incremental slow feature analysis (f-incsfa) [Abstract] [BibTeX] [URL]	Conference on Neural Networks (IJCNN), The 2012 International Joint , 1-6. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: The proposed Fast Incremental Slow Feature Analysis (F-IncSFA) which is considered as unsupervised learning and it can be used for extracting the features. The featurescan represent the fundamental components of the modifications in different aspect and especially in posing and temporally firms and consistent even in high-dimensional input like signal, video, etc. Here, we addressed a development in SFA algorithm as compare with latest one [17] by combining Candid Covariance-Free Incremental Principle components Analysis (CCIPCA) and Minor Components Analysis (MCA).The proposed F-IncSFA can adapts along with non-stationary environments and unlike the latest SFA, which has two times using CCIPCA, has one time using CCIPCA in its algorithm which makes the method simpler yet efficient. We examine the proposed approach by using some video sequences of humanoid robot and also it is compared with CCIPCA in several experiments and the result indicates that it indeed has superior outcome and impart informative slow features that is representing significant abstract from possessions of non-stationary environment and poses. We successfully apply the F-IncSFA on the high-dimensional video and extract abstract object data. We extend our F-IncSFA to networks in hierarchical model, and apply it for extraction of features in the information obtained from high-dimensional video and the results were promising.
BibTeX: @inproceedings{YousefiLoo-2012, author = {Yousefi, Bardia and Loo, Chu Kiong}, title = {Development of fast incremental slow feature analysis (f-incsfa)}, booktitle = {Conference on Neural Networks (IJCNN), The 2012 International Joint}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2012}, pages = {1--6}, url = {http://ieeexplore.ieee.org/document/6252847/}, doi = {http://doi.org/10.1109/ijcnn.2012.6252847} }
Yousefi, B. & Loo, C.K.	2014	Development of biological movement recognition by interaction between active basis model and fuzzy optical flow division [Abstract] [BibTeX] [URL]	The Scientific World Journal , 2014. Publ. Hindawi Publishing Corporation.	article
Abstract: Following the study on computational neuroscience through functional magnetic resonance imaging claimed that human action recognition in the brain of mammalian pursues two separated streams, that is, dorsal and ventral streams. It follows up by two pathways in the bioinspired model, which are specialized for motion and form information analysis (Giese and Poggio 2003). Active basis model is used to form information which is different from orientations and scales of Gabor wavelets to form a dictionary regarding object recognition (human). Also biologically movement optic-flow patterns utilized. As motion information guides share sketch algorithm in form pathway for adjustment plus it helps to prevent wrong recognition. A synergetic neural network is utilized to generate prototype templates, representing general characteristic form of every class. Having predefined templates, classifying performs based on multitemplate matching. As every human action has one action prototype, there are some overlapping and consistency among these templates. Using fuzzy optical flow division scoring can prevent motivation for misrecognition. We successfully apply proposed model on the human action video obtained from KTH human action database. Proposed approach follows the interaction between dorsal and ventral processing streams in the original model of the biological movement recognition. The attained results indicate promising outcome and improvement in robustness using proposed approach.
BibTeX: @article{YousefiLoo-2014a, author = {Yousefi, Bardia and Loo, Chu Kiong}, title = {Development of biological movement recognition by interaction between active basis model and fuzzy optical flow division}, journal = {The Scientific World Journal}, publisher = {Hindawi Publishing Corporation}, year = {2014}, volume = {2014}, url = {http://downloads.hindawi.com/journals/tswj/2014/238234.pdf}, doi = {http://doi.org/10.1155/2014/238234} }
Yousefi, B. & Loo, C.K.	2014	Comparative study on interaction of form and motion processing streams by applying two different classifiers in mechanism for recognition of biological movement [Abstract] [BibTeX] [URL]	The Scientific World Journal , 2014. Publ. Hindawi Publishing Corporation.	article
Abstract: Research on psychophysics, neurophysiology, and functional imaging shows particular representation of biological movements which contains two pathways. The visual perception of biological movements formed through the visual system called dorsal and ventral processing streams. Ventral processing stream is associated with the form information extraction; on the other hand, dorsal processing stream provides motion information. Active basic model (ABM) as hierarchical representation of the human object had revealed novelty in form pathway due to applying Gabor based supervised object recognition method. It creates more biological plausibility along with similarity with original model. Fuzzy inference system is used for motion pattern information in motion pathway creating more robustness in recognition process. Besides, interaction of these paths is intriguing and many studies in various fields considered it. Here, the interaction of the pathways to get more appropriated results has been investigated. Extreme learning machine (ELM) has been implied for classification unit of this model, due to having the main properties of artificial neural networks, but crosses from the difficulty of training time substantially diminished in it. Here, there will be a comparison between two different configurations, interactions using synergetic neural network and ELM, in terms of accuracy and compatibility.
BibTeX: @article{YousefiLoo-2014b, author = {Yousefi, Bardia and Loo, Chu Kiong}, title = {Comparative study on interaction of form and motion processing streams by applying two different classifiers in mechanism for recognition of biological movement}, journal = {The Scientific World Journal}, publisher = {Hindawi Publishing Corporation}, year = {2014}, volume = {2014}, url = {http://downloads.hindawi.com/journals/tswj/2014/723213.pdf}, doi = {http://doi.org/10.1155/2014/723213} }
Yousefi, B. & Loo, C.K.	2015	A dual fast and slow feature interaction in biologically inspired visual recognition of human action [Abstract] [BibTeX] [URL]	e-print arXiv:1509.02587 .	article
Abstract: Computational neuroscience studies that have examined human visual system through functional magnetic resonance imaging (fMRI) have identified a model where the mammalian brain pursues two distinct pathways (for recognition of biological movement tasks). In the brain, dorsal stream analyzes the information of motion (optical flow), which is the fast features, and ventral stream (form pathway) analyzes form information (through active basis model based incremental slow feature analysis ) as slow features. The proposed approach suggests the motion perception of the human visual system composes of fast and slow feature interactions that identifies biological movements. Form features in the visual system biologically follows the application of active basis model with incremental slow feature analysis for the extraction of the slowest form features of human objects movements in the ventral stream. Applying incremental slow feature analysis provides an opportunity to use the action prototypes. To extract the slowest features episodic observation is required but the fast features updates the processing of motion information in every frames. Experimental results have shown promising accuracy for the proposed model and good performance with two datasets (KTH and Weizmann).
BibTeX: @article{YousefiLoo-2015, author = {Yousefi, Bardia and Loo, Chu Kiong}, title = {A dual fast and slow feature interaction in biologically inspired visual recognition of human action}, journal = {e-print arXiv:1509.02587}, year = {2015}, url = {https://arxiv.org/abs/1509.02587} }
Yousefi, B. & Loo, C.K.	2016	Slow feature action prototypes effect assessment in mechanism for recognition of biological movement ventral stream [Abstract] [BibTeX] [URL(2)]	International Journal of Bio-Inspired Computation , 8(6), 410-424. Publ. Inderscience Publishers (IEL).	article
Abstract: In analysis of the brain and visual system functionality, scientific evidence points to two independent processing pathways in recognising biological movement, i.e. dorsal and ventral streams. Motion information generated in the dorsal processing stream is presented as fuzzy optical flow division while ventral processing stream with information of the object form is implemented as an active basis model. The recognition task however still requires decision-making and mutual interaction between these pathways. This process is done using slow features as action prototypes dictionary of biological movements. For motion information interaction, dorsal pathway guides the shared sketch algorithm that leads to decision-making for a more accurate outcome. Extreme learning machine classifier is used for decision-making unit kernel. The proposed approach is tested on the KTH human action database videos. Good performances are indicated compared to existing methods, with good interaction between dorsal and ventral processing streams.
BibTeX: @article{YousefiLoo-2016, author = {Yousefi, Bardia and Loo, Chu Kiong}, title = {Slow feature action prototypes effect assessment in mechanism for recognition of biological movement ventral stream}, journal = {International Journal of Bio-Inspired Computation}, publisher = {Inderscience Publishers (IEL)}, year = {2016}, volume = {8}, number = {6}, pages = {410--424}, url2 = {https://umexpert.um.edu.my/file/publication/00011927_145223.pdf} }
Yu, W. & Zhao, C.	2019	Recursive Exponential Slow Feature Analysis for Fine-Scale Adaptive Processes Monitoring With Comprehensive Operation Status Identification [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Industrial Informatics , 15(6), 3311-3323.	article
Abstract: Due to the compensation of the control loops, industrial processes under feedback control generally reveal typical dynamic behaviors for different operation statuses. Conventional adaptive methods may update model falsely and thus result in invalid monitoring results, since they cannot effectively extract the feedback dynamic information and fail to accurately differentiate real anomalies from normal process changes. In this study, a recursive exponential slow feature analysis (ESFA) algorithm is developed for fine-scale adaptive monitoring to solve the problem of false model updating. First, an ESFA method is proposed to nonlinearly extract slow features, so that the general trend of the process variations can be better captured. On the basis of the ESFA model, a fine-scale adaptive monitoring scheme is developed to accurately capture the normal changes of industrial processes, including normal slow varying and normal shift of operation conditions. In this way, the normal slow varying can be effectively distinguished from incipient faults with unusual dynamic behaviors to avoid falsely adapting for the fault case, and the monitoring model can be correctly updated for new operation status after distinguishing real process anomalies from normal shifts of operation conditions. A simulation process and two real industrial processes are adopted to validate the performance of the proposed adaptive monitoring method. Experimental results show that the proposed method can effectively identify different operation statuses to decide whether to update the monitoring model or to raise an alarm.
BibTeX: @article{8513886, author = {Yu, Wanke and Zhao, Chunhui}, title = {Recursive Exponential Slow Feature Analysis for Fine-Scale Adaptive Processes Monitoring With Comprehensive Operation Status Identification}, journal = {IEEE Transactions on Industrial Informatics}, year = {2019}, volume = {15}, number = {6}, pages = {3311-3323}, url = {https://ieeexplore.ieee.org/abstract/document/8513886?casa_token=LXN0zIcfNTwAAAAA:W-uDsIMt8Op4kGUp7bpjXGJZdG5li0XAMUti1NOdjfjkHv28T20CHbE4eT8UJv0s_7g7N0kcJk5j}, url2 = {https://www.researchgate.net/publication/328603437_Recursive_Exponential_Slow_Feature_Analysis_for_Fine-Scale_Adaptive_Processes_Monitoring_With_Comprehensive_Operation_Status_Identification}, doi = {http://doi.org/10.1109/TII.2018.2878405} }
Zafeiriou, L.; Antonakos, E.; Zafeiriou, S. & Pantic, M.	2014	Joint unsupervised face alignment and behaviour analysis [Abstract] [BibTeX] [URL] [URL(2)]	European Conference on Computer Vision , 167-183.	inproceedings
Abstract: The predominant strategy for facial expressions analysis and temporal analysis of facial events is the following: a generic facial landmarks tracker, usually trained on thousands of carefully annotated examples, is applied to track the landmark points, and then analysis is performed using mostly the shape and more rarely the facial texture. This paper challenges the above framework by showing that it is feasible to perform joint landmarks localization (i.e. spatial alignment) and temporal analysis of behavioural sequence with the use of a simple face detector and a simple shape model. To do so, we propose a new component analysis technique, which we call Autoregressive Component Analysis (ARCA), and we show how the parameters of a motion model can be jointly retrieved. The method does not require the use of any sophisticated landmark tracking methodology and simply employs pixel intensities for the texture representation.
BibTeX: @inproceedings{ZafeiriouAntonakosEtAl-2014, author = {Zafeiriou, Lazaros and Antonakos, Epameinondas and Zafeiriou, Stefanos and Pantic, Maja}, title = {Joint unsupervised face alignment and behaviour analysis}, booktitle = {European Conference on Computer Vision}, year = {2014}, pages = {167--183}, url = {http://link.springer.com/chapter/10.1007/978-3-319-10593-2_12}, url2 = {https://pdfs.semanticscholar.org/d3f9/cf3fb66326e456587acb18cf3196d1e314c7.pdf}, doi = {http://doi.org/10.1007/978-3-319-10593-2_12} }
Zafeiriou, L.; Nicolaou, M.A.; Zafeiriou, S.; Nikitidis, S. & Pantic, M.	2016	Probabilistic slow features for behavior analysis [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Neural Networks and Learning Systems , 27(5), 1034-1048. Publ. IEEE.	article
Abstract: A recently introduced latent feature learning technique for time-varying dynamic phenomena analysis is the so-called slow feature analysis (SFA). SFA is a deterministic component analysis technique for multidimensional sequences that, by minimizing the variance of the first-order time derivative approximation of the latent variables, finds uncorrelated projections that extract slowly varying features ordered by their temporal consistency and constancy. In this paper, we propose a number of extensions in both the deterministic and the probabilistic SFA optimization frameworks. In particular, we derive a novel deterministic SFA algorithm that is able to identify linear projections that extract the common slowest varying features of two or more sequences. In addition, we propose an expectation maximization (EM) algorithm to perform inference in a probabilistic formulation of SFA and similarly extend it in order to handle two and more time-varying data sequences. Moreover, we demonstrate that the probabilistic SFA (EM-SFA) algorithm that discovers the common slowest varying latent space of multiple sequences can be combined with dynamic time warping techniques for robust sequence time-alignment. The proposed SFA algorithms were applied for facial behavior analysis, demonstrating their usefulness and appropriateness for this task.
BibTeX: @article{ZafeiriouNicolaouEtAl-2016, author = {Lazaros Zafeiriou and Mihalis A. Nicolaou and Stefanos Zafeiriou and Symeon Nikitidis and Maja Pantic}, title = {Probabilistic slow features for behavior analysis}, journal = {{IEEE} Transactions on Neural Networks and Learning Systems}, publisher = {IEEE}, year = {2016}, volume = {27}, number = {5}, pages = {1034--1048}, url = {http://ieeexplore.ieee.org/document/7120134/}, url2 = {https://pdfs.semanticscholar.org/8622/19876548998e67c229b445779cd002dfb2e7.pdf}, doi = {http://doi.org/10.1109/TNNLS.2015.2435653} }
Zafeiriou, L.; Nicolaou, M.; Zafeiriou, S.; Nikitidis, S.; Pantic, M. & others	2013	Learning slow features for behaviour analysis [BibTeX]	Conference on Computer Vision (ICCV), 2013 IEEE International , 2840-2847.	inproceedings
BibTeX: @inproceedings{ZafeiriouNicolaouEtAl-2013a, author = {Zafeiriou, Lazaros and Nicolaou, Mihalis and Zafeiriou, Stefanos and Nikitidis, Symeon and Pantic, Maja and others}, title = {Learning slow features for behaviour analysis}, booktitle = {Conference on Computer Vision (ICCV), 2013 IEEE International}, year = {2013}, pages = {2840--2847} }
Zafeiriou, L.; Nikitidis, S.; Zafeiriou, S. & Pantic, M.	2014	Slow features nonnegative matrix factorization for temporal data decomposition [Abstract] [BibTeX] [URL] [URL(2)]	2014 IEEE International Conference on Image Processing (ICIP) , 1430-1434.	inproceedings
Abstract: In this paper, we combine the principles of temporal slowness and nonnegative parts-based learning into a single framework that aims to learn slow varying parts-based representations of time varying sequences. We demonstrate that the proposed algorithm arises naturally by embedding the Slow Features Analysis trace optimization problem in the nonnegative subspace learning framework and derive novel multiplicative update rules for its optimization. The usefulness of the developed algorithm is demonstrated for unsupervised facial behaviour dynamics analysis on MMI database.
BibTeX: @inproceedings{ZafeiriouNikitidisEtAl-2014, author = {Zafeiriou, Lazaros and Nikitidis, Symeon and Zafeiriou, Stefanos and Pantic, Maja}, title = {Slow features nonnegative matrix factorization for temporal data decomposition}, booktitle = {2014 IEEE International Conference on Image Processing (ICIP)}, year = {2014}, pages = {1430--1434}, url = {http://ieeexplore.ieee.org/document/7025286/}, url2 = {https://pdfs.semanticscholar.org/8674/3f25dd12a559c58f85623768a8a8eb0572a3.pdf}, doi = {http://doi.org/10.1109/icip.2014.7025286} }
Zafeiriou, S.; Nicolaou, M.A. & Pantic, M.	2013	A unified framework for probabilistic component analysis [Abstract] [BibTeX] [URL(2)]	CoRR . Publ. Citeseer.	article
Abstract: In this paper, we present a unifying framework which reduces the construction of probabilistic component analysis techniques to a mere selection of the latent neighbourhood via the prior, thus providing an elegant and principled framework for creating novel component analysis models. Under our framework, we unify many very popular and well-studied component analysis algorithms, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Locality Preserving Projections (LPP) and Slow Feature Analysis (SFA). We rstly show that the projection directions produced by all the aforementioned methods are also produced by the Maximum Likelihood (ML) solution of a single joint probability density function (PDF) just by choosing an appropriate prior over the latent space in our framework. Subsequently, we propose novel Expectation Maximization (EM) algorithms utilising the proposed joint PDF. Theoretical analysis and experiments show the usefulness of the proposed framework.
BibTeX: @article{ZafeiriouNicolaouEtAl-2013b, author = {Zafeiriou, Stefanos and Nicolaou, Mihalis A and Pantic, Maja}, title = {A unified framework for probabilistic component analysis}, journal = {CoRR}, publisher = {Citeseer}, year = {2013}, url2 = {https://pdfs.semanticscholar.org/f1cd/c3bcd4bce67c113f2c30ec5c85ed2ce037fc.pdf} }
Zhang, H.; Deng, X.; Zhang, Y.; Hou, C. & Li, C.	2020	Dynamic nonlinear batch process fault detection and identification based on two‐directional dynamic kernel slow feature analysis [Abstract] [BibTeX]	Canadian Journal of Chemical Engineering .	article
Abstract: The batch process generally covers high nonlinearity and two-directional dynamics: time-wise dynamics, which correspond to inherently time-varying dynamics resulting from the slowly varying underlying driving forces within each batch duration; and batch-wise dynamics, which are associated with different operating modes among different batches. However, most existing dynamic nonlinear monitoring methods cannot extract the slowly varying underlying driving forces of the nonlinear batch process and rarely tackle the batch-wise dynamic characteristics among batch runs. In order to address these issues, a new monitoring scheme based on two-directional dynamic kernel slow feature analysis (TDKSFA) is developed by combining kernel SFA with a global modelling strategy. In the TDKSFA method, kernel SFA is integrated with the ARMAX time series model to mine the nonlinear and time-wise dynamic properties within a batch run due to its capability of extracting the slowly varying underlying driving forces. Furthermore, the global modelling strategy is presented to handle the batch-wise dynamics among batches by calculating the total average kernel matrix of all training batches. After the slow features are extracted, Hotelling's T2 and SPE statistics are built to detect faults. To solve the issue of fault variable nonlinear identification, a novel nonlinear contribution plot inspired by the pseudo-sample variable projection trajectories in the TDKSFA model is further proposed to identify fault variables. Finally, the feasibility and effectiveness of the TDKSFA-based fault diagnosis strategy is demonstrated through a numerical system and the penicillin fermentation process.
BibTeX: @article{Zhang2020DynamicNB, author = {Hanyuan Zhang and Xiaogang Deng and Yunchu Zhang and Chuanjing Hou and Chengdong Li}, title = {Dynamic nonlinear batch process fault detection and identification based on two‐directional dynamic kernel slow feature analysis}, journal = {Canadian Journal of Chemical Engineering}, year = {2020} }
Zhang, H.; Li, C.; Li, D.; Zhang, Y. & Peng, W.	2021	Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics [Abstract] [BibTeX] [URL(2)]	Energy and Buildings , 253, 111467.	article
Abstract: Air handling unit (AHU) is a typical special batch control process, exhibiting strong nonlinear property and two-directional dynamic characteristics which are the time-wise and batch-wise dynamic characteristics. Specifically, the time-wise dynamic characteristic corresponds to the evolution of different operating modes caused by the underlying driving forces which vary slowly in each running day (a batch run), while the batch-wise dynamic characteristic relates to the dynamic variations and deviations among different running days (batch runs). In order to further improve the AHU FDD performance through capturing the underlying driving forces of the AHU system and tackling the batch-wise dynamic property between different batch runs, in this paper, an enhanced kernel slow feature analysis (SFA) based FDD scheme is developed to detect and identify the faults of the nonlinear AHU system. Firstly, a three-way data based kernel SFA (TBKSFA) approach is proposed to detect the faults. In the proposed TBKSFA approach, the kernel trick is adopted in the SFA to sufficiently deal with the nonlinearity and the time-wise dynamic characteristic, and the multiway data analysis is employed to cope with the batch-wise dynamics among different batch runs by converting the three-way training dataset into a variable-wise unfolding two-way matrix. In addition, to handle the tough problem of nonlinearly identifying the fault pattern, a novel kernel discriminant SFA (KDSFA) model is further built by combining the kernel SFA with the discriminant analysis method. In the fault pattern diagnosis process, the proposed KDSFA is pairwisely implemented on the normal and fault datasets to calculate the fault direction, and the fault is then identified by computing the similar degrees of its own fault direction and the historical fault directions. At last, experiments and comparisons on the FDD performance of the developed approach are made using the experimental data provided by ASHRAE Research Project RP-1312. To be specific, the proposed TBKSFA based fault detection method is compared with the popular kernel principal component analysis (KPCA) method, the closely related kernel SFA method and the emerging manifold learning based kernel locality preserving projections (KLPP) method. While the developed KDSFA based fault pattern diagnosis scheme is compared with the conventional jointed angle analysis technique, the strongly linked DSFA based method and the rising artificial neural networks based long short-term memory(LSTM) classifier. Experimental results demonstrate that significant improvements can be achieved by the proposed approach compared with some other popular methods.
BibTeX: @article{ZHANG2021111467, author = {Hanyuan Zhang and Chengdong Li and Ding Li and Yunchu Zhang and Wei Peng}, title = {Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics}, journal = {Energy and Buildings}, year = {2021}, volume = {253}, pages = {111467}, url2 = {https://www.sciencedirect.com/science/article/pii/S0378778821007519}, doi = {http://doi.org/10.1016/j.enbuild.2021.111467} }
Zhang, H.; Tian, X. & Cai, L.	2015	Nonlinear process fault diagnosis using kernel slow feature discriminant analysis [Abstract] [BibTeX] [URL]	IFAC-PapersOnLine , 48(21), 607-612.	article
Abstract: Slow feature analysis (SFA) is an unsupervised liner learning algorithm and lacks the ability to consider class label information and data nonlinearity. In this paper, a novel nonlinear process fault diagnosis approach is proposed based on kernel slow feature discriminant analysis (kernel SFDA), which incorporates the discriminative information into SFA\ learning and uses the kernel trick to deal with nonlinear characteristics of process data. The directions of fault data that maximize the temporal variation of between-class pseudo-time series and minimize the temporal variation of within-class pseudo-time series simultaneously are calculated by pairwise kernel SFDA. Then, the fault pattern is identified by measuring the similarity between its own fault direction and the directions of historical fault datasets. The simulation results on the continuous stirred tank reactor system demonstrate that the proposed method can recognize the pattern of fault snapshot data more effectively than conventional methods.
BibTeX: @article{ZhangTianEtAl-2015b, author = {Hanyuan Zhang and Xuemin Tian and Lianfang Cai}, title = {Nonlinear process fault diagnosis using kernel slow feature discriminant analysis}, journal = {IFAC-PapersOnLine}, year = {2015}, volume = {48}, number = {21}, pages = {607--612}, url = {http://www.sciencedirect.com/science/article/pii/S240589631501722X}, doi = {http://doi.org/10.1016/j.ifacol.2015.09.593} }
Zhang, H.; Tian, X. & Deng, X.	2017	Batch Process Monitoring Based on Multiway Global Preserving Kernel Slow Feature Analysis [BibTeX]	IEEE Access , 5, 2696-2710. Publ. IEEE.	article
BibTeX: @article{ZhangTianEtAl-2017, author = {Hanyuan Zhang and Xuemin Tian and Xiaogang Deng}, title = {Batch Process Monitoring Based on Multiway Global Preserving Kernel Slow Feature Analysis}, journal = {IEEE Access}, publisher = {IEEE}, year = {2017}, volume = {5}, pages = {2696-2710} }
Zhang, H.; Tian, X.; Deng, X. & Cao, Y.	2018	Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis [Abstract] [BibTeX] [URL(2)]	ISA Transactions , 79, 108-126.	article
Abstract: As an attractive nonlinear dynamic data analysis tool, global preserving kernel slow feature analysis (GKSFA) has achieved great success in extracting the high nonlinearity and inherently time-varying dynamics of batch process. However, GKSFA is an unsupervised feature extraction method and lacks the ability to utilize batch process class label information, which may not offer the most effective means for dealing with batch process monitoring. To overcome this problem, we propose a novel batch process monitoring method based on the modified GKSFA, referred to as discriminant global preserving kernel slow feature analysis (DGKSFA), by closely integrating discriminant analysis and GKSFA. The proposed DGKSFA method can extract discriminant feature of batch process as well as preserve global and local geometrical structure information of observed data. For the purpose of fault detection, a monitoring statistic is constructed based on the distance between the optimal kernel feature vectors of test data and normal data. To tackle the challenging issue of nonlinear fault variable identification, a new nonlinear contribution plot method is also developed to help identifying the fault variable after a fault is detected, which is derived from the idea of variable pseudo-sample trajectory projection in DGKSFA nonlinear biplot. Simulation results conducted on a numerical nonlinear dynamic system and the benchmark fed-batch penicillin fermentation process demonstrate that the proposed process monitoring and fault diagnosis approach can effectively detect fault and distinguish fault variables from normal variables.
BibTeX: @article{ZHANG2018108, author = {Hanyuan Zhang and Xuemin Tian and Xiaogang Deng and Yuping Cao}, title = {Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis}, journal = {ISA Transactions}, year = {2018}, volume = {79}, pages = {108-126}, url2 = {https://www.sciencedirect.com/science/article/pii/S0019057818301721}, doi = {http://doi.org/10.1016/j.isatra.2018.05.005} }
Zhang, H.; Tian, X.; Deng, X. & Cao, Y.	2018	Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis [BibTeX]	ISA transactions , 79, 108-126. Publ. Elsevier.	article
BibTeX: @article{ZhangTianEtAl-2018, author = {Zhang, Hanyuan and Tian, Xuemin and Deng, Xiaogang and Cao, Yuping}, title = {Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis}, journal = {ISA transactions}, publisher = {Elsevier}, year = {2018}, volume = {79}, pages = {108--126}, doi = {http://doi.org/10.1016/j.isatra.2018.05.005} }
Zhang, L.; Lu, X. & Yuan, Y.	2013	Slow feature analysis for multi-camera activity understanding [Abstract] [BibTeX] [URL]	Conference on Virtual Reality and Visualization (ICVRV), 2013 International , 241-244.	inproceedings
Abstract: Multi-camera activity analysis is a key point in video surveillance of many wide-area scenes, such as airports, underground stations, shopping mall and road junctions. On the basis of previous work, this paper presents a new feature learning method based on Slow Feature Analysis (SFA) to understand activities observed across the network of cameras. The main contribution of this paper can be summarized as follows: (1) It is the first time that SFA-based learning method is introduced to multi-camera activity understanding, (2) It presents an evaluation to examine the effectiveness of SFA-based method to facilitate the learning of inter-camera activity pattern dependencies, and (3) It estimates the sensitivity of learning inter-camera time delayed dependency given different training size, which is a critical factor for accurate dependency learning and has not been largely studied by existing work before. Experiments are carried out on a dataset obtained in a trident roadway. The results demonstrate that the SFA-based method outperforms the sate of the art.
BibTeX: @inproceedings{ZhangLuEtAl-2013, author = {Zhang, Lei and Lu, Xiaoqiang and Yuan, Yuan}, title = {Slow feature analysis for multi-camera activity understanding}, booktitle = {Conference on Virtual Reality and Visualization (ICVRV), 2013 International}, year = {2013}, pages = {241--244}, url = {http://ieeexplore.ieee.org/abstract/document/6689426/}, doi = {http://doi.org/10.1109/icvrv.2013.46} }
Zhang, L.; Wu, C. & Du, B.	2014	Automatic radiometric normalization for multitemporal remote sensing imagery with iterative slow feature analysis [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Geoscience and Remote Sensing , 52(10), 6141-6155. Publ. IEEE.	article
Abstract: Multitemporal imagery analysis has attracted widespread interest in recent years due to the large number of applications. Multitemporal remote sensing imagery analysis is very important for Earth observation, in order to allow an understanding of the relationships and interactions between human and natural phenomena. Radiometric variance of the same targets due to differences in environmental conditions is one of the most important issues. In this paper, we propose an automatic radiometric normalization method with iterative slow feature analysis (ISFA) to reduce the radiometric variance. Slow feature analysis extracts invariant features from the quickly varying input signals. It is first reformulated for the multitemporal imagery problem and then improved to an iterative version. In the iteration, high weights are assigned to unchanged pixels. After convergence, the linear function of the radiometric normalization is directly obtained with all the pixels and their weights. If the ISFA is negatively affected by the changed pixels in some special cases and cannot find the correct regression line, initial seeds are selected as the initial weights in the iteration, to improve the performance, which is called S-ISFA. Two pairs of multitemporal ETM images from different seasons and years were used to test the effectiveness of our proposed method. The quantitative evaluation showed that our proposed method performs better, with smaller differences in the statistical distributions and radiometric values than the other state-of-the-art methods. The robustness with regard to the selection of initial seeds was also proved in the experiment.
BibTeX: @article{ZhangWuEtAl-2014, author = {Zhang, Liangpei and Wu, Chen and Du, Bo}, title = {Automatic radiometric normalization for multitemporal remote sensing imagery with iterative slow feature analysis}, journal = {IEEE Transactions on Geoscience and Remote Sensing}, publisher = {IEEE}, year = {2014}, volume = {52}, number = {10}, pages = {6141--6155}, url = {http://ieeexplore.ieee.org/document/6737226/}, url2 = {https://pdfs.semanticscholar.org/7da1/69ca40873c5ae1b72370def79a3009030340.pdf}, doi = {http://doi.org/10.1109/tgrs.2013.2295263} }
Zhang, N.; Tian, X.; Cai, L. & Deng, X.	2015	Process fault detection based on dynamic kernel slow feature analysis [Abstract] [BibTeX] [URL]	Computers & Electrical Engineering , 41, 9-17.	article
Abstract: Abstract A fault detection method based on dynamic kernel slow feature analysis (DKSFA) is presented in the paper. SFA\ is a new feature extraction technology which can find a group of slowly varying feature outputs from the high-dimensional inputs. In order to analyze the nonlinear dynamic characteristics of the process data, DKSFA\ is presented which applies the augmented matrix to consider the dynamic characteristic and uses kernel slow feature analysis (KSFA) to extract the nonlinear slow features hidden in the observed data. For the purpose of fault detection, the D monitoring statistic index is built based on DKSFA\ model and its confidence limit is computed by kernel density estimation. Simulations on a nonlinear system and Tennessee Eastman (TE) benchmark process show that the proposed method has a better fault detection performance compared with the conventional (kernel principal component analysis) KPCA-based method.
BibTeX: @article{ZhangTianEtAl-2015a, author = {Ni Zhang and Xuemin Tian and Lianfang Cai and Xiaogang Deng}, title = {Process fault detection based on dynamic kernel slow feature analysis}, journal = {Computers \& Electrical Engineering}, year = {2015}, volume = {41}, pages = {9--17}, url = {http://www.sciencedirect.com/science/article/pii/S0045790614002729}, doi = {http://doi.org/10.1016/j.compeleceng.2014.11.003} }
Zhang, S. & Zhao, C.	2018	Slow feature analysis based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly [BibTeX]	IEEE Transactions on Industrial Electronics . Publ. IEEE.	article
BibTeX: @article{ZhangZhao-2018, author = {Zhang, Shumei and Zhao, Chunhui}, title = {Slow feature analysis based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly}, journal = {IEEE Transactions on Industrial Electronics}, publisher = {IEEE}, year = {2018}, doi = {http://doi.org/10.1109/tie.2018.2853603} }
Zhang, Z.; Huang, K.; Tan, T.; Yang, P. & Li, J.	2016	ReD-SFA: relation discovery based slow feature analysis for trajectory clustering [Abstract] [BibTeX] [URL] [URL(2)]	Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 752-760. Publ. Institute of Electrical and Electronics Engineers (IEEE).	inproceedings
Abstract: For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data. In this paper, we proposed an approach, named Relation Discovery based Slow Feature Analysis (ReD-SFA), for feature learning and graph construction simultaneously. Given an initial graph with only a few nearest but most reliable pairwise relations, new reliable relations are discovered by an assumption of reliability preservation, i.e., the reliable relations will preserve their reliabilities in the learnt projection subspace. We formulate the idea as a cross entropy (CE) minimization problem to reduce the discrepancy between two Bernoulli distributions parameterized by the updated distances and the existing relation graph respectively. Furthermore, to overcome the imbalanced distribution of samples, a Boosting-like strategy is proposed to balance the discovered relations over all clusters. To evaluate the proposed method, extensive experiments are performed with various trajectory clustering tasks, including motion segmentation, time series clustering and crowd detection. The results demonstrate that ReDSFA can discover reliable intra-cluster relations with high precision, and competitive clustering performance can be achieved in comparison with state-of-the-art.
BibTeX: @inproceedings{ZhangHuangEtAl-2016, author = {Zhang, Zhang and Huang, Kaiqi and Tan, Tieniu and Yang, Peipei and Li, Jun}, title = {{ReD}-{SFA}: relation discovery based slow feature analysis for trajectory clustering}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2016}, pages = {752--760}, url = {http://ieeexplore.ieee.org/document/7780457/}, url2 = {https://pdfs.semanticscholar.org/23a5/9bfb96c4f543673e05b3cf6dc01b4173745b.pdf}, doi = {http://doi.org/10.1109/cvpr.2016.88} }
Zhang, Z. & Tao, D.	2012	Slow feature analysis for human action recognition [Abstract] [BibTeX] [URL]	IEEE Transactions on Pattern Analysis and Machine Intelligence , 34(3), 436-450. Publ. Institute of Electrical and Electronics Engineers (IEEE).	article
Abstract: Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal [1]. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD--SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. Experimental results suggest that the SFA-based approach (1) is able to extract useful motion patterns and improves the recognition performance, (2) requires less intermediate processing steps but achieves comparable or even better performance, and (3) has good potential to recognize complex multiperson activities.
BibTeX: @article{ZhangTao-2012, author = {Zhang Zhang and Dacheng Tao}, title = {Slow feature analysis for human action recognition}, journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, year = {2012}, volume = {34}, number = {3}, pages = {436--450}, url = {http://ieeexplore.ieee.org/document/6136516/}, doi = {http://doi.org/10.1109/TPAMI.2011.157} }
Zhao, L.; Huang, X. & Yu, R.	2020	Slow Feature Analysis Based Quality Prediction for Slow Time-Varying Batch Processes [Abstract] [BibTeX] [URL]	2020 7th International Conference on Information Science and Control Engineering (ICISCE) , 1291-1295.	inproceedings
Abstract: Batch processes require effective quality analysis and prediction techniques to ensure product quality. In this paper, quality prediction work has been carried out for multiphase batch processes with slow time-varying characteristics based on the slow feature analysis (SFA) algorithm. To analyze the slow time-varying characteristics along the batch direction, sliding windows are constructed in the batch direction covering different batches, and accordingly a series of models are established using the SFA algorithm to capture the slow feature of the varying relationship between the process variables and the quality. At last, the proposed strategy is applied to the quality analysis and prediction of a typical slow time-varying batch process, the start-up process of the injection molding process, and the prediction results are compared with those obtained by the strategy using partial least squares (PLS) to build the regression models. The results verify the effectiveness of the proposed method in the quality prediction of slow time-varying batch processes.
BibTeX: @inproceedings{9532398, author = {Zhao, Luping and Huang, Xin and Yu, Rongjian}, title = {Slow Feature Analysis Based Quality Prediction for Slow Time-Varying Batch Processes}, booktitle = {2020 7th International Conference on Information Science and Control Engineering (ICISCE)}, year = {2020}, pages = {1291-1295}, url = {https://ieeexplore.ieee.org/document/9532398}, doi = {http://doi.org/10.1109/ICISCE50968.2020.00261} }
Zhao, R.; Du, B.; Zhang, L. & Zhang, L.	2016	Beyond background feature extraction: an anomaly detection algorithm inspired by slowly varying signal analysis [Abstract] [BibTeX] [URL] [URL(2)]	IEEE Transactions on Geoscience and Remote Sensing , 54(3), 1757-1774. Publ. IEEE.	article
Abstract: Background feature extraction is an important step in hyperspectral anomaly detection. However, the lack of prior information about anomaly targets and the complex spectral mix- ture result in a challenge for robust background feature extraction. Can we solve the anomaly detection problem other than with background feature extraction? Relative to anomalies, the back- ground spectral signal is usually stable and slowly varying. In view of this point, slowly varying background analysis is introduced into anomaly detection in this paper. The desired background sig- nals are obtained through a generalized eigenvalue decomposition problem based on the original data and the differential image. The extracted signals are then combined with a Mahalanobis distance metric to construct the detection estimation. Different data processing procedures and signal extraction patterns are re- spectively formulated to construct different versions of the slowly varying background-signal-based detector. The performances of the proposed methods were validated on both synthetic and real hyperspectral data. The experimental results reveal that the pro- posed methods outperform the state-of-the-art anomaly detectors, with superior receiver operating characteristic (ROC) curves, area-under-ROC values, and background–target separation. The sensitivity of the relevant parameters was also analyzed in an experimental analysis.
BibTeX: @article{ZhaoDuEtAl-2016, author = {Zhao, Rui and Du, Bo and Zhang, Liangpei and Zhang, Lefei}, title = {Beyond background feature extraction: an anomaly detection algorithm inspired by slowly varying signal analysis}, journal = {{IEEE} Transactions on Geoscience and Remote Sensing}, publisher = {IEEE}, year = {2016}, volume = {54}, number = {3}, pages = {1757--1774}, url = {http://ieeexplore.ieee.org/document/7317572/}, url2 = {https://www.researchgate.net/publication/301346350_Beyond_Background_Feature_Extraction_An_Anomaly_Detection_Algorithm_Inspired_by_Slowly_Varying_Signal_Analysis}, doi = {http://doi.org/10.1109/tgrs.2015.2488285} }
Zheng, H.; Jiang, Q. & Yan, X.	2019	Quality‐relevant dynamic process monitoring based on Mutual Information Multiblock slow feature analysis [Abstract] [BibTeX]	Journal of Chemometrics , 33(4).	article
Abstract: Slow feature analysis (SFA) is an efficient technique in exploring process dynamic information and is suitable for quality‐relevant process monitoring. However, involving quality‐irrelevant variables or features may introduce redundant information and degrade the monitoring performance. A novel multiblock monitoring scheme based on mutual information (MI) and SFA isproposed to detect an efficient quality‐relevant fault for dynamic processes.First, all process variables are divided into two blocks in accordance with theirMI values with quality variables. Second, slow features (SFs) of two blocks are extracted via the SFA. The SFs, which are extract ed from the quality‐relevant variables, are not all related to the quality variable. Thus, these SFs are further partitioned into two blocks in accordance with their MI values with quality variables. The SFs from three blocks are obtained, and monitoring statistics are constructed. Two simulation studies, including a numerical example and Tennessee Eastman process, demonstrate that the proposed method outper-forms conventional methods.
BibTeX: @article{zheng_jiang_yan_2019, author = {Zheng, Haiyong and Jiang, Qingchao and Yan, Xuefeng}, title = {Quality‐relevant dynamic process monitoring based on Mutual Information Multiblock slow feature analysis}, journal = {Journal of Chemometrics}, year = {2019}, volume = {33}, number = {4}, doi = {http://doi.org/10.1002/cem.3110} }
Zheng, J. & Zhao, C.	2019	Process Monitoring under Closed-loop Control with Performance-relevant Full Decomposition of Slow Feature Analysis [Abstract] [BibTeX] [URL]	2019 12th Asian Control Conference (ASCC) , 1672-1677.	inproceedings
Abstract: Close-loop control is widely used in modern industrial process which brings obvious process dynamics. Disturbances on process may be compensated by the control actions, and thus it may have little influence on the process performance like product quality and waste discharge. Therefore, process monitoring without considering the influences of process variations on performance and process dynamics may cause nuisance alarms. To achieve comprehensive process monitoring, performance-relevant full decomposition of slow feature analysis, termed PFDSFA here, is proposed for processes under closed-loop control by simultaneously considering the influences of process variations and control actions on performance and process dynamics. First, the proposed algorithm extracts variations directly relevant to performance variables using canonical correlation analysis. In this way, process variable space can be decomposed into performance-relevant subspace and process-relevant subspace. Next, static and dynamic variations of each subspace are extracted to distinguish operating condition deviations from real faults. The proposed monitoring structure offers a fine-scale decomposition of process variations, and also achieves comprehensive process monitoring of process static and dynamic characteristics. Besides, it can effectively indicate whether a disturbance influences the performance and process dynamics. Finally, the proposed method is applied to the Tennessee Eastman process to terrify the efficacy.
BibTeX: @inproceedings{8764967, author = {Zheng, Jiale and Zhao, Chunhui}, title = {Process Monitoring under Closed-loop Control with Performance-relevant Full Decomposition of Slow Feature Analysis}, booktitle = {2019 12th Asian Control Conference (ASCC)}, year = {2019}, pages = {1672-1677}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8764967} }
Zheng, J. & Zhao, C.	2019	Online monitoring of performance variations and process dynamic anomalies with performance-relevant full decomposition of slow feature analysis [Abstract] [BibTeX] [URL(2)]	Journal of Process Control , 80, 89-102.	article
Abstract: Closed-loop control is widely used in modern industrial processes to ensure that process performance such as product quality and waste discharge are maintained at the predefined set-points. However, control actions which may compensate the disturbances on process performance and result in obvious process dynamics cause great challenges to process monitoring. The influences of control actions on process performance and dynamics for process monitoring have not been fully investigated before. Thus, a performance-relevant full decomposition of slow feature analysis termed PFDSFA here, is proposed for process monitoring under closed-loop control by simultaneously considering the influences of process variations on process performance and dynamics. First, the new algorithm extracts variations which are closely relevant to performance variables using canonical correlation analysis. Based on it, process variable space can be decomposed into performance-relevant subspace and process-relevant subspace. Then, both static and dynamic variations of each subspace are extracted to design monitoring statistics which can distinguish normal operating condition deviations from dynamic anomalies incurred by real faults. The proposed PFDSFA algorithm offers a fine-scale decomposition of process variations and achieves comprehensive process monitoring of process static and dynamic characteristics. Besides, it is efficient in indicating whether disturbances make influence on process performance and dynamics. Finally, two case studies are employed to illustrate the applicability and efficacy of the proposed algorithm in comparison with some other monitoring approaches.
BibTeX: @article{ZHENG201989, author = {Jiale Zheng and Chunhui Zhao}, title = {Online monitoring of performance variations and process dynamic anomalies with performance-relevant full decomposition of slow feature analysis}, journal = {Journal of Process Control}, year = {2019}, volume = {80}, pages = {89-102}, url2 = {https://www.sciencedirect.com/science/article/pii/S0959152418305687}, doi = {http://doi.org/10.1016/j.jprocont.2019.05.004} }
Zhong, W.; Jiang, C.; Peng, X.; Li, Z. & Qian, F.	2018	Online Quality Prediction of Industrial Terephthalic Acid Hydropurification Process Using Modified Regularized Slow-Feature Analysis [BibTeX]	Industrial & Engineering Chemistry Research , 57(29), 9604-9614. Publ. ACS Publications.	article
BibTeX: @article{ZhongJiangEtAl-2018, author = {Zhong, Weimin and Jiang, Chao and Peng, Xin and Li, Zhi and Qian, Feng}, title = {Online Quality Prediction of Industrial Terephthalic Acid Hydropurification Process Using Modified Regularized Slow-Feature Analysis}, journal = {Industrial \& Engineering Chemistry Research}, publisher = {ACS Publications}, year = {2018}, volume = {57}, number = {29}, pages = {9604--9614}, doi = {http://doi.org/10.1021/acs.iecr.8b01270} }
Zhu, L.; Li, Z. & Chen, J.	2020	An industrial process monitoring scheme with moving window slow feature analysis [Abstract] [BibTeX] [URL]	IFAC-PapersOnLine , 53(2), 11996-12001.	article
Abstract: With the development of the modern industries, the requirement for comprehensive and effective monitoring scheme of the industrial production process is growing significantly. Conventional monitoring methods treat the deviations as the abnormities and thus result in the invalid monitoring results, because the dynamic information cannot be extracted accurately, which may be caused by the transient process or new operation conditions, and real faults cannot be separated from the normal process changes. To cope with this limitation, a moving window slow feature analysis is proposed in this paper. First, the temporal dynamic features of the industrial production process are extracted to separate the temporal dynamics from the steady state. Second, an adaptive monitoring strategy is presented to accurately acquire the normal changes of the production process, including the normal shift of operation conditions and the slow time-varying behaviors, through updating model parameters and monitoring statistics when a query sample comes. In this way, the real dynamic anomalies can be distinguished from the normal dynamic behaviors and reduce the false alarms effectively. Finally, the effectiveness and practicality are demonstrated through an evaporation process.
BibTeX: @article{ZHU202011996, author = {Li Zhu and Zhe Li and Junghui Chen}, title = {An industrial process monitoring scheme with moving window slow feature analysis}, journal = {IFAC-PapersOnLine}, year = {2020}, volume = {53}, number = {2}, pages = {11996-12001}, url = {https://www.sciencedirect.com/science/article/pii/S2405896320310478}, doi = {http://doi.org/10.1016/j.ifacol.2020.12.728} }
Zito, T.	2012	Exploring the slowness principle in the auditory domain. [Abstract] [BibTeX] [URL]	PhD thesis, Institute for Biology, Humboldt University Berlin, Germany .	phdthesis
Abstract: In this thesis we develop models and algorithms based on the slowness principle in the auditory domain. Several experimental results as well as the successful results in the visual domain indicate that, despite the different nature of the sensory signals, the slowness principle may play an important role in the auditory domain as well, if not in the cortex as a whole. Different modeling approaches have been used, which make use of several alternative representations of the auditory stimuli. We show the limitations of these approaches. In the domain of signal processing, the slowness principle and its straightforward implementation, the Slow Feature Analysis algorithm, has been proven to be useful beyond biologically inspired modeling. A novel algorithm for nonlinear blind source separation is described that is based on a combination of the slowness and the statistical independence principles, and is evaluated on artificial and real-world audio signals. The Modular toolkit for Data Processing open source software library is additionally presented.
BibTeX: @phdthesis{Zito-2012, author = {Tiziano Zito}, title = {Exploring the slowness principle in the auditory domain.}, school = {Institute for Biology}, year = {2012}, url = {http://edoc.hu-berlin.de/docviews/abstract.php?id=39096} }
Zito, T. & Wiskott, L.	2006	Diagonalization of time-delayed covariance matrices does not guarantee statistical independence in high-dimensional feature space. [BibTeX]	Proc. ICA Research Network International Workshop, Sep 18-19, Liverpool, UK , 120-122.	inproceedings
BibTeX: @inproceedings{ZitoWiskott-2006, author = {Tiziano Zito and Laurenz Wiskott}, title = {Diagonalization of time-delayed covariance matrices does not guarantee statistical independence in high-dimensional feature space.}, booktitle = {Proc.\ ICA Research Network International Workshop, Sep 18-19, Liverpool, UK}, year = {2006}, pages = {120--122} }

Created by JabRef on 25/11/2023. Original JabRef Export Filter by Mark Schenk and Holger Jeromin, adapted at RUB INI.

List of Publications about Slow Feature Analysis (compiled by Laurenz Wiskott)

List of Publications about Slow Feature Analysis
(compiled by Laurenz Wiskott)