no code implementations • 21 Dec 2023 • Tom F. Sterkenburg
This paper considers the epistemic justification for a simplicity preference in inductive inference that may be obtained from the machine learning framework of statistical learning theory.
no code implementations • 10 Feb 2022 • Tom F. Sterkenburg
We study computable PAC (CPAC) learning as introduced by Agarwal et al. (2020).
no code implementations • 9 Feb 2022 • Tom F. Sterkenburg, Peter D. Grünwald
The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification.