Michael Kirchhof is a PhD student at the Explainable Machine Learning group and the Human-Computer Interaction group, co-supervised by Prof. Zeynep Akata and Prof. Enkelejda Kasneci at the University of Tübingen. He received his B. Sc. (2018) and M. Sc. (2021) in Statistics with distinction at TU Dortmund University where he focussed on probabilistic modeling and machine learning. In 2019, he was a research intern at BMW Group, Munich. His research goal is to introduce explanations to safety-critical classification tasks. To this end, he is interested in the structure of learned representations and the dualities between probability theory and machine learning.