Best approximation to C2 functions and its error bounds using regular-center gaussian networks

Binfan Liu, Jennie Si

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

1 Citation (Scopus)

Abstract

Gaussian neural networks are considered to approximate any C2 function with support on the unit hypercube Im = [0,1]m in the sense of best approximation. An upper bound (O(N-2)) of the approximation error is obtained in the present paper for a Gaussian network having Nm hidden neurons with centers defined on a regular mesh in Im.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages2400-2406
Number of pages7
Volume4
StatePublished - 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period6/27/946/29/94

Fingerprint

Neurons
Neural networks

ASJC Scopus subject areas

  • Software

Cite this

Liu, B., & Si, J. (1994). Best approximation to C2 functions and its error bounds using regular-center gaussian networks. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 4, pp. 2400-2406). Piscataway, NJ, United States: IEEE.

Best approximation to C2 functions and its error bounds using regular-center gaussian networks. / Liu, Binfan; Si, Jennie.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 Piscataway, NJ, United States : IEEE, 1994. p. 2400-2406.

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

Liu, B & Si, J 1994, Best approximation to C2 functions and its error bounds using regular-center gaussian networks. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 4, IEEE, Piscataway, NJ, United States, pp. 2400-2406, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 6/27/94.
Liu B, Si J. Best approximation to C2 functions and its error bounds using regular-center gaussian networks. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4. Piscataway, NJ, United States: IEEE. 1994. p. 2400-2406
Liu, Binfan ; Si, Jennie. / Best approximation to C2 functions and its error bounds using regular-center gaussian networks. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 Piscataway, NJ, United States : IEEE, 1994. pp. 2400-2406
@inproceedings{9d55da972da94f40bb0aa1aab2bafce8,
title = "Best approximation to C2 functions and its error bounds using regular-center gaussian networks",
abstract = "Gaussian neural networks are considered to approximate any C2 function with support on the unit hypercube Im = [0,1]m in the sense of best approximation. An upper bound (O(N-2)) of the approximation error is obtained in the present paper for a Gaussian network having Nm hidden neurons with centers defined on a regular mesh in Im.",
author = "Binfan Liu and Jennie Si",
year = "1994",
language = "English (US)",
volume = "4",
pages = "2400--2406",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Best approximation to C2 functions and its error bounds using regular-center gaussian networks

AU - Liu, Binfan

AU - Si, Jennie

PY - 1994

Y1 - 1994

N2 - Gaussian neural networks are considered to approximate any C2 function with support on the unit hypercube Im = [0,1]m in the sense of best approximation. An upper bound (O(N-2)) of the approximation error is obtained in the present paper for a Gaussian network having Nm hidden neurons with centers defined on a regular mesh in Im.

AB - Gaussian neural networks are considered to approximate any C2 function with support on the unit hypercube Im = [0,1]m in the sense of best approximation. An upper bound (O(N-2)) of the approximation error is obtained in the present paper for a Gaussian network having Nm hidden neurons with centers defined on a regular mesh in Im.

UR - http://www.scopus.com/inward/record.url?scp=0028748447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028748447&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028748447

VL - 4

SP - 2400

EP - 2406

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -