Best approximation properties and error bounds of gaussian networks

Binfan Liu, Jennie Si

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

4 Citations (Scopus)

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
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages2798-2801
Number of pages4
Volume3
ISBN (Print)0780312988
StatePublished - 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

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

  • Chemical Health and Safety
  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality

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 (Vol. 3, pp. 2798-2801). Piscataway, NJ, United States: Publ by IEEE.

Best approximation properties and error bounds of gaussian networks. / Liu, Binfan; Si, Jennie.

Proceedings of the IEEE Conference on Decision and Control. ed. / Anon. Vol. 3 Piscataway, NJ, United States : Publ by IEEE, 1993. p. 2798-2801.

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

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. vol. 3, Publ by IEEE, Piscataway, NJ, United States, pp. 2798-2801, Proceedings of the 32nd IEEE Conference on Decision and Control. Part 3 (of 4), San Antonio, TX, USA, 12/15/93.
Liu B, Si J. Best approximation properties and error bounds of gaussian networks. In Anon, editor, Proceedings of the IEEE Conference on Decision and Control. Vol. 3. Piscataway, NJ, United States: Publ by IEEE. 1993. p. 2798-2801
Liu, Binfan ; Si, Jennie. / Best approximation properties and error bounds of gaussian networks. Proceedings of the IEEE Conference on Decision and Control. editor / Anon. Vol. 3 Piscataway, NJ, United States : Publ by IEEE, 1993. pp. 2798-2801
@inproceedings{678cc3b55b234a15801f09c7003c44d9,
title = "Best approximation properties and error bounds of gaussian networks",
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.",
author = "Binfan Liu and Jennie Si",
year = "1993",
language = "English (US)",
isbn = "0780312988",
volume = "3",
pages = "2798--2801",
editor = "Anon",
booktitle = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Best approximation properties and error bounds of gaussian networks

AU - Liu, Binfan

AU - Si, Jennie

PY - 1993

Y1 - 1993

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0027735783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027735783&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027735783

SN - 0780312988

VL - 3

SP - 2798

EP - 2801

BT - Proceedings of the IEEE Conference on Decision and Control

A2 - Anon, null

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -