• Home
• Writings
• Teaching
• Contact

I am Emmy Noether junior group leader at the Munich Center for Mathematical Philosophy (MCMP, LMU Munich). I am also a fellow of the Konrad Zuse School of Excellence in Reliable AI (relAI) and a member of the Young Center of the LMU Center for Advanced Studies (CAS^LMU).

I am interested in applying the mathematical field of machine learning theory to philosophical questions around machine learning and artificial intelligence. My Emmy Noether project From Bias to Knowledge: The Epistemology of Machine Learning is concerned with the fundamental notion of inductive bias—the assumptions that allow a learning algorithm to learn. This project builds on my earlier German Science Foundation-funded project on the The Epistemology of Statistical Learning Theory.

I think climate change is a thing, and I don't see why we all couldn't try to make an effort. So I avoid flying, and aim to only travel to places I can reach by train.

Contact me at tom.sterkenburglmu.de.

Current affairs

I have an open position for a postdoctoral fellow. The application deadline is the 1st of December, the intended starting date is the 1st of April 2025. You can find more details here.

Nov 2023. I give a talk for the LMU research colloquium in ethics of AI.

Oct 2024. My paper "Statistical learning theory and Occam's razor: The core argument" has been accepted for publication in Minds and Machines.

Oct 2024. Sara Jensen (supervised by Karen Crowther and myself) visits us from Oslo for the semester. Welcome, Sara!

Oct 2024. In the 2024-25 winter semester I teach an advanced seminar on Epistemology and Theory of Machine Learning. I also organize, together with Timo Freiesleben, a new round of the MCMP reading group on philosophy of machine learning.

Oct 2024. Katia Parshina starts as a PhD student in my project. Welcome, Katia!

Formerly current affairs...

Previously

In my DFG-funded Eigene Stelle project The Epistemology of Statistical Learning Theory (2020-2023), I explored the epistemological import of statistical learning theory, the standard theoretical framework for modern machine learning methods. I also proved new results in the recently proposed setting of computable PAC learning.

As a postdoctoral fellow at the MCMP (2017-2020), I investigated the meta-inductive justification of induction that is based on the machine learning theory of online prediction. I further worked on a Bayesian confirmation theory that can deal with newly formulated hypotheses, that also drew from results in online prediction.

In my PhD project (2013-2018, cum laude), at the CWI and the Faculty of Philosophy of the University of Groningen, I investigated the theory of universal prediction stemming from algorithmic information theory (Kolmogorov complexity). My PhD dissertation on Universal Prediction won me the Wolfgang Stegmüller Award.

I hold a MSc in Logic (Institute for Logic, Language and Computation, University of Amsterdam, cum laude), a MSc in History and Philosophy of Science (Descartes Centre, Utrecht University, cum laude), and a BSc in Artificial Intelligence (VU University Amsterdam, cum laude). I have never managed to obtain my driver's license, but I hope to attain Deutsche Bahn Statuslevel Gold Platin soon.