Výsledky vyhledávání - "Sterkenburg, Tom F."

Report

Statistical learning theory and Occam's razor: The core argument

Autor: Sterkenburg, Tom F.

Statistical learning theory is often associated with the principle of Occam's razor, which recommends a simplicity preference in inductive inference. This paper distills the core argument for simplicity obtainable from statistical learning theory, bu

Externí odkaz: http://arxiv.org/abs/2312.13842

Zobrazit plný text záznamu

Report

On characterizations of learnability with computable learners

Autor: Sterkenburg, Tom F.

Publikováno v: Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), PMLR 178:3365-3379, 2022

We study computable PAC (CPAC) learning as introduced by Agarwal et al. (2020). First, we consider the main open question of finding characterizations of proper and improper CPAC learning. We give a characterization of a closely related notion of str

Externí odkaz: http://arxiv.org/abs/2202.05041

Zobrazit plný text záznamu

Report

The no-free-lunch theorems of supervised learning

Autor: Sterkenburg, Tom F., Grünwald, Peter D.

Publikováno v: Synthese 199:9979-10015 (2021)

The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing p

Externí odkaz: http://arxiv.org/abs/2202.04513

Zobrazit plný text záznamu

Akademický článek

Statistical Learning Theory and Occam’s Razor: The Core Argument.

Autor: Sterkenburg, Tom F.

Publikováno v: Minds & Machines; Mar2025, Vol. 35 Issue 1, p1-28, 28p

Zobrazit plný text záznamu

Report

A generalized characterization of algorithmic probability

Autor: Sterkenburg, Tom F.

An a priori semimeasure (also known as "algorithmic probability" or "the Solomonoff prior" in the context of inductive inference) is defined as the transformation, by a given universal monotone Turing machine, of the uniform measure on the infinite s

Externí odkaz: http://arxiv.org/abs/1508.05733

Zobrazit plný text záznamu