Prof. Dr. Ullrich Köthe

I’m heading the subgroup on “Explainable Machine Learning”. Explainable learning shall open-up the blackbox of successful machine learning algorithms, in particular neural networks, to provide insight rather than mere numbers. To this end, we are designing powerful new algorithms on the basis of invertible neural networks and apply them to medicine, image analysis, and the natural and life sciences.

In addition, I’m interested in generic software bringing state-of-the-art algorithms to the end user and maintain the VIGRA image analysis library.