Dr. Tom Sterkenburg

Further Information

Tom Sterkenburg is Emmy Noether junior group leader of the project From Bias to Knowledge: The Epistemology of Machine Learning. This project builds on his earlier German Science Foundation-funded project on The Epistemology of Statistical Learning Theory. Before coming to the MCMP, he did his PhD at the Department of Theoretical Philosophy of the University of Groningen and the Dutch national research center for mathematics and computer science (CWI Amsterdam). His PhD thesis on universal prediction received the Wolfgang-Stegmüller-Award of the German Society for Analytic Philosophy.

Research Interests

Tom’s research is in the philosophy of induction and the epistemological foundations of machine learning. He is in particular interested in applying the mathematical theory of machine learning to philosophical questions around machine learning and artificial intelligence.

Selected Publications

1. Sterkenburg, T.F.: On explaining the success of induction. The British Journal for the Philosophy of Science (forthcoming).
2. Stewart, R.T., Sterkenburg, T.F.: Peirce, pedigree, Probability. Transactions of the Charles S. Peirce Society 58(2): 138-166 (2022).
3. Sterkenburg, T.F.: On characterization of learnability with computable learners. Proceedings of Machine Learning Research 178 (COLT 2022): 3365-3379 (2022).
4. Sterkenburg, T.F., De Heide, R.: On the truth-convergence of open-minded Bayesianism. The Review of Symbolic Logic 15(1): 64-100 (2022).
5. Sterkenburg, T.F., Grünwald, P.D.: The no-free-lunch theorems of supervised learning. Synthese 199: 9979-10015 (2021).
6. Sterkenburg, T.F.: The meta-inductive justification of induction. Episteme 17(4): 519-541 (2020).
7. Sterkenburg, T.F.: The meta-inductive justification of induction: The pool of strategies. Philosophy of Science 86(5): 981-992 (2019).
8. Sterkenburg, T.F.: Putnam’s diagonal argument and the impossibility of a universal learning machine. Erkenntnis 84(3): 633-656 (2018).
9. Sterkenburg, T.F.: A generalized characterization of algorithmic probability. Theory of Computing Systems 61(4): 1337-1352 (2017).
10. Sterkenburg, T.F.: Solomonoff prediction and Occam’s razor. Philosophy of Science 83(4): 459-479 (2016).