Center for Neurophilosophy and Ethics of Neurosciences
print


Breadcrumb Navigation


Content
Timo Freiesleben

Timo Freiesleben, B.Sc., M.A.

About Me

I am a Ph.D. student at the Graduate School of Systemic Neurosciences under the supervision of Prof. Dr. Stephan Hartmann. Before that, I obtained a B.Sc. in Mathematics from the Eberhard Karls Universität Tübingen and an M.A. In Logic and Philosophy of Science at the MCMP/LMU Munich, where, next to my other studies I also took courses in computer science. During my Bachelors, I have spent one year at the University of Oslo.

Research Interests

My PhD project focuses on explainable artificial intelligence (XAI) and aims overall at making the decisions of modern machine learning algorithms more transparent to human agents. I am interested in giving a (formal) framework for XAI that is built on a solid philosophical and psychological basis. In particular, I want to research counterfactual explanations. My more narrow goal is to develop and test bio-inspired formal models that generate counterfactual explanations for the decisions of black box algorithms.
In my Master thesis, I built a formal, normative decision theory that takes human intuitions into account. During that time, I got also highly interested in frameworks of bounded rationality (H. Simon, S. Russell, D. Kahneman, etc.), theories of human information processing, and dual-process theories. My broader interests include (group) decision making (under uncertainty), causality & explanation, deep learning, philosophy & ethics of AI, and probability theory.