Best approximation properties and error bounds of gaussian networks

Binfan Liu, Jennie Si

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

The best approximation of any C2 function with support on the unit hypercube Im in Rm is considered in the present paper. We prove that a Gaussian radial basis network with centers defined on a regular mesh in Rm has the best approximation property. Moreover, an upper bound (O(NMIN2)) of the approximation is obtained for a network having Nm units.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Conference on Decision and Control
Editors Anon
PublisherPubl by IEEE
Pages2798-2801
Number of pages4
ISBN (Print)0780312988
StatePublished - Dec 1 1993
EventProceedings of the 32nd IEEE Conference on Decision and Control. Part 3 (of 4) - San Antonio, TX, USA
Duration: Dec 15 1993Dec 17 1993

Publication series

NameProceedings of the IEEE Conference on Decision and Control
Volume3
ISSN (Print)0191-2216

Other

OtherProceedings of the 32nd IEEE Conference on Decision and Control. Part 3 (of 4)
CitySan Antonio, TX, USA
Period12/15/9312/17/93

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

Liu, B., & Si, J. (1993). Best approximation properties and error bounds of gaussian networks. In Anon (Ed.), Proceedings of the IEEE Conference on Decision and Control (pp. 2798-2801). (Proceedings of the IEEE Conference on Decision and Control; Vol. 3). Publ by IEEE.