A three layer neural network can represent any multivariate function

DOI10.1016/J.JMAA.2023.127096MaRDI QIDQ6355370arXivFDO

Authors Vugar E. Ismailov

Publication date 5 December 2020

Published in arXiv

Full work available at URL https://doi.org/10.1016/J.JMAA.2023.127096

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Multidimensional problems (41A63) Artificial neural networks and deep learning (68T07)

arXiv classification

cs.LGmath.FAstat.ML

Abstract: In 1987, Hecht-Nielsen showed that any continuous multivariate function can be implemented by a certain type three-layer neural network. This result was very much discussed in neural network literature. In this paper we prove that not only continuous functions but also all discontinuous functions can be implemented by such neural networks.

This page was built for publication: A three layer neural network can represent any multivariate function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6355370)