Our research in autonomous robotics is aimed at demonstrating that neural dynamic architectures of embodied cognition can generate object-oriented actions and simple forms of cognition. We organize the work around a scenario in which a partially autonomous robot system interacts with human operators with whom they share a natural environment.
In the Computational Neurology group, we answer clinical relevant questions in the field of neuropsychiatry using computational methods. We analyze clinical and neuroimaging data using both data-driven and theory-based modeling. This integration helps generating a better (qualitative) and robust (quantitative) understanding of pathophysiological processes of neurological diseases, as well as their diagnosis and treatment.
Our group investigates the neural mechanisms underlying learning and memory using computational methods. The main language of communication is English. We welcome students who would like to pursue a Bachelor/Master thesis or an internship in our group. Our unit is located at the Institute of Neural Computation and is a member of the Mercator Research Group (MRG) "Structure of Memory".
In a broad perspective, my main research ambition is to understand the fundamental computational principles of learning that characterize intelligence. More specifically, my research interests are focussed on the development, analysis, and application of deep learning models and methods. I am particularly interested in analyzing and developing probabilistic models and inference methods, investigating biologically plausible deep learning, and understanding the stochastic processes involved in the training and optimisation of neural networks and probabilistic models.
We develop advanced analysis methods to apply them to neural and behavioural data, and combine them with computational models. In close collaboration with experimental research groups we analyse and model large data sets of electrophysiological recordings. Our goal is to identify the neural mechanisms underlying cognitive control, in particular in prefrontal and basal ganglia circuits, and to determine how the neuromodulator dopamine contributes to them. We use a variety of analysis and computational modelling techniques, such as machine learning approaches and numerical simulations of single neuron and network activity.
Our goal is to develop state-of-the-art machine learning models that can scale while being energy-efficient.
We develop a neurally grounded theory of embodied cognition. A number of exemplary problems are chosen to provide access to important basic properties of embodied cognitive systems that are open to experiment and modeling. The main theoretical tools are attractor dynamics and dynamic field theory.
The Theory of Machine Learning workgroup is concerned with the design and analysis of adaptive information processing systems. We are interested in systems that improve over time through learning, self-adaptation, and evolution. Our systems improve autonomously based on data, in contrast to manual instruction or programming.
We are an interdisciplinary research group focusing on principles of self-organization in neural systems, ranging from artificial neural networks to the hippocampus. By bringing together machine learning and computational neuroscience we explore ways of extracting representations from data that are useful for goal-directed learning.
Trustworthy Machine Learning: investigating novel approaches to privacy-preserving federated learning, the theoretical foundations of deep learning, and collaborative training of explainable models.
Our research focuses on understanding visual information processing in the brain. We investigate how manifold parameters given in natural visual sceneries are represented in real-time across large neuronal populations using voltage-sensitive dye imaging (VSDI).
The Institut für Neuroinformatik (INI) is a research unit of the Faculty of Computer Science at the Ruhr-Universität Bochum. Its scientific goal is to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory and effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental psychology and neurophysiology as well as machine learning, neural artificial intelligence, computer vision, and robotics.
Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany
Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210