Constructive uniform approximation of differentiable vector-functions by neural network methods

Moshe Shoam, Mark Meltser, Larry M. Manevitz

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

A method for constructively approximating any twice differentiable function in the uniform (i.e. maximal error) norm by successive changes in the weights and number of neurons in a neural network is developed. This is a realization of the approximation results of Cybenko, White, Gallant, Loshno and others. The constructive approximation in the uniform norm is more appropriate for, e.g. certain robotic applications, and stands in contrast with more standard methods, such as back-propagation which approximate only in the average error norm.

Original languageAmerican English
Title of host publicationWorld Congress on Neural Networks
PagesII.372-II.378
Volume2
ISBN (Electronic)9781315784076
StatePublished - 10 Sep 2021

All Science Journal Classification (ASJC) codes

  • General Psychology

Fingerprint

Dive into the research topics of 'Constructive uniform approximation of differentiable vector-functions by neural network methods'. Together they form a unique fingerprint.

Cite this