EUVIMEDOpdag EUVIMED
Crossref

Approximation by superpositions of a sigmoidal function

G. Cybenko

Mathematics of Control, Signals, and Systems · 1989-12 · 2 (4) · 303-314

DOI: 10.1007/bf02551274 ↗

At a glance

Journal article in Mathematics of Control, Signals, and Systems, 1989-12. Written by G. Cybenko. Cited 11577 times so far (Crossref); 28 references.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single hidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well approximated by continuous feedforward neural networks with only a single internal, hidden layer and any continuous sigmoidal nonlinearity. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks.

Cite

APA

Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2(4), 303-314. https://doi.org/10.1007/bf02551274

Vancouver

Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems. 1989;2(4):303-314. doi:10.1007/bf02551274

BibTeX
@article{Cybenko1989,
  author = {Cybenko, G.},
  title = {Approximation by superpositions of a sigmoidal function},
  journal = {Mathematics of Control, Signals, and Systems},
  year = {1989},
  volume = {2},
  number = {4},
  pages = {303--314},
  doi = {10.1007/bf02551274}
}
Start for free →