Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Estimation of Overfitting Degree of Algebraic Machine Learning in Boolean Algebra

Estimation of Overfitting Degree of Algebraic Machine Learning in Boolean Algebra The paper presents an estimation of overfitting probability for VKF-method of algebraic machine learning in the simplest case of Boolean algebra without counter-examples. The model uses the Vapnik—Chervonenkis proposal to minimize the empirical risk. Asymptotically the probability of overfitting errors for a fixed fraction of test examples tends to zero faster than exponentially decrease if the description length and the number of requested hypotheses go to infinity. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Automatic Documentation and Mathematical Linguistics Springer Journals

Estimation of Overfitting Degree of Algebraic Machine Learning in Boolean Algebra

Download PDF
3 pages

Loading next page...
 
/lp/springer-journals/estimation-of-overfitting-degree-of-algebraic-machine-learning-in-YoesovKOPB

References (8)

Publisher
Springer Journals
Copyright
Copyright © Allerton Press, Inc. 2022. ISSN 0005-1055, Automatic Documentation and Mathematical Linguistics, 2022, Vol. 56, No. 3, pp. 160–162. © Allerton Press, Inc., 2022. Russian Text © The Author(s), 2022, published in Nauchno-Tekhnicheskaya Informatsiya, Seriya 2: Informatsionnye Protsessy i Sistemy, 2022, No. 6, pp. 17–19.
ISSN
0005-1055
eISSN
1934-8371
DOI
10.3103/s0005105522030098
Publisher site
See Article on Publisher Site

Abstract

The paper presents an estimation of overfitting probability for VKF-method of algebraic machine learning in the simplest case of Boolean algebra without counter-examples. The model uses the Vapnik—Chervonenkis proposal to minimize the empirical risk. Asymptotically the probability of overfitting errors for a fixed fraction of test examples tends to zero faster than exponentially decrease if the description length and the number of requested hypotheses go to infinity.

Journal

Automatic Documentation and Mathematical Linguistics – Springer Journals

Published: Jun 1, 2022

Keywords: empirical risk; overfitting; VKF-method; Boolean algebra

There are no references for this article.