| Lab courses | An Introduction to Python for Data Analysis |
| Project seminar | Machine Learning: Unsupervised Methods (with Problem Based Learning) |
| Lab courses | Introduction to Python |
| Project seminar | Machine Learning: Unsupervised Methods (with Problem Based Learning) |
| Lab courses | Introduction to Python |
We adapt the Area Under the Margin (AUM) method to gradient-boosted decision tree classifiers for detecting label errors in tabular defect classification data. Our single-run approach matches computationally expensive cross-validation baselines and has been successfully deployed in real-world steel surface inspection workflows.
Our research explores explainable object detection by utilizing prototypal features. This approach enables the development of transparent AI models where the decision-making process is visualized and can be intuitively understood, enhancing user trust and allowing for interaction.
tachAId is an interactive guide offering concrete recommendations for developing human-centered AI across its lifecycle. It helps stakeholders build user-focused AI by addressing key challenges like fairness and transparency, bridging ethical principles with technical solutions.
We empirically decompose the generalization loss of deep neural networks into bias and variance components on an image classification task by constructing ensembles using geometric-mean averaging of the sub-net outputs and we isolate double descent at the variance component of the loss. Our results show that small models afford ensembles that outperform single large models while requiring considerably fewer parameters and computational steps. We also find that deep double descent that depends on the existence of label noise can be mitigated by using ensembles of models subject to identical label noise almost as thoroughly as by ensembles of networks each trained subject to i.i.d. noise.
The Institut für Neuroinformatik (INI) is a research unit of the Faculties of Computer Science and Medicine 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
