English

An Algorithm for Approximating Continuous Functions on Compact Subsets with a Neural Network with one Hidden Layer

Machine Learning 2019-02-12 v1 Functional Analysis Machine Learning

Abstract

George Cybenko's landmark 1989 paper showed that there exists a feedforward neural network, with exactly one hidden layer (and a finite number of neurons), that can arbitrarily approximate a given continuous function ff on the unit hypercube. The paper did not address how to find the weight/parameters of such a network, or if finding them would be computationally feasible. This paper outlines an algorithm for a neural network with exactly one hidden layer to reconstruct any continuous scalar or vector valued continuous function.

Keywords

Cite

@article{arxiv.1902.03638,
  title  = {An Algorithm for Approximating Continuous Functions on Compact Subsets with a Neural Network with one Hidden Layer},
  author = {Elliott Zaresky-Williams},
  journal= {arXiv preprint arXiv:1902.03638},
  year   = {2019}
}

Comments

6 pages

R2 v1 2026-06-23T07:37:03.875Z