Approximation of Binary-Valued Functions by Networks of Finite VC Dimension

Authors: Věra Kůrková
Publication year: 2023
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Artificial Neural Networks and Machine Learning – ICANN 2023. Proceedings, Part I
Projects: AppNeCo: Approximate Neurocomputing
Bibliographic citation: KŮRKOVÁ, Věra. Approximation of Binary-Valued Functions by Networks of Finite VC Dimension. In: ILIADIS, L., PAPALEONIDAS, A., ANGELOV, P., JAYNE, C., eds. Artificial Neural Networks and Machine Learning – ICANN 2023. Proceedings, Part I. Cham: Springer, 2023, S. 483-490. Lecture Notes in Computer Science, 14254. ISBN 978-3-031-44206-3. ISSN 0302-9743
Dostupné z: doi:10.1007/978-3-031-44207-0_40.
DOI: 10.1007/978-3-031-44207-0_40
ID: 577075
Online record: View online record

Abstract

Distributions of errors in approximation of binary-valued functions by networks with sets of input-output functions of finite VC dimension is investigated. Conditions on concentration of approximation errors around their mean values are derived in terms of growth functions of sets of input-output functions. Limitations of approximation capabilities of networks of finite VC dimension are discussed.