The Best Approximation to C2 Functions and its Error Bounds Using Regular-Center Gaussian Networks

Binfan Liu, Jennie Si

Research output: Contribution to journalArticle

23 Scopus citations

Abstract

Gaussian neural networks are considered to approximate any C2function with support on the unit hypercube Im= [0,1]min the sense of best approximation. An upper bound (O(N–2)) of the approximation error is obtained in the present letter for a Gaussian network having N m hidden neurons with centers defined on a regular mesh in Im.

Original languageEnglish (US)
Pages (from-to)845-847
Number of pages3
JournalIEEE Transactions on Neural Networks
Volume5
Issue number5
DOIs
StatePublished - Sep 1994

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'The Best Approximation to C2 Functions and its Error Bounds Using Regular-Center Gaussian Networks'. Together they form a unique fingerprint.

  • Cite this