Constructing stochastic networks via β-RBF networks

Sheng Tun Li, Ernst L. Leiss

Research output: Contribution to conferencePaper

Abstract

Without considering spatial, stochastic, and temporal features inherent in natural neural systems, the computational power of conventional artificial neural networks (ANNs) is limited. In the present paper, we look at the stochastic complexity and construct a stochastic ANN by modeling stochastic fluctuations in the environmental stimuli such that all stimuli are prone to be corrupted by noise or even outliers and to break networks down; therefore, a positive-breakdown network is required. We investigate the stochasticity in the domain of function approximation (estimation) in the framework of radial basis function networks (RBFNs) and propose a robust RBFN, β-RBFN, by applying the breakdown point approach in robust regression. Experimental results demonstrate the advantages of the proposed networks in robustness and simplicity over the plain RBFNs.

Original languageEnglish
Pages19-24
Number of pages6
Publication statusPublished - 1996 Jan 1
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: 1996 Jun 31996 Jun 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period96-06-0396-06-06

Fingerprint

Radial basis function networks
Neural networks

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Li, S. T., & Leiss, E. L. (1996). Constructing stochastic networks via β-RBF networks. 19-24. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .
Li, Sheng Tun ; Leiss, Ernst L. / Constructing stochastic networks via β-RBF networks. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .6 p.
@conference{44ff36b63fca4418806cdb9e072ec0a5,
title = "Constructing stochastic networks via β-RBF networks",
abstract = "Without considering spatial, stochastic, and temporal features inherent in natural neural systems, the computational power of conventional artificial neural networks (ANNs) is limited. In the present paper, we look at the stochastic complexity and construct a stochastic ANN by modeling stochastic fluctuations in the environmental stimuli such that all stimuli are prone to be corrupted by noise or even outliers and to break networks down; therefore, a positive-breakdown network is required. We investigate the stochasticity in the domain of function approximation (estimation) in the framework of radial basis function networks (RBFNs) and propose a robust RBFN, β-RBFN, by applying the breakdown point approach in robust regression. Experimental results demonstrate the advantages of the proposed networks in robustness and simplicity over the plain RBFNs.",
author = "Li, {Sheng Tun} and Leiss, {Ernst L.}",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "19--24",
note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

Li, ST & Leiss, EL 1996, 'Constructing stochastic networks via β-RBF networks', Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 96-06-03 - 96-06-06 pp. 19-24.

Constructing stochastic networks via β-RBF networks. / Li, Sheng Tun; Leiss, Ernst L.

1996. 19-24 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Constructing stochastic networks via β-RBF networks

AU - Li, Sheng Tun

AU - Leiss, Ernst L.

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Without considering spatial, stochastic, and temporal features inherent in natural neural systems, the computational power of conventional artificial neural networks (ANNs) is limited. In the present paper, we look at the stochastic complexity and construct a stochastic ANN by modeling stochastic fluctuations in the environmental stimuli such that all stimuli are prone to be corrupted by noise or even outliers and to break networks down; therefore, a positive-breakdown network is required. We investigate the stochasticity in the domain of function approximation (estimation) in the framework of radial basis function networks (RBFNs) and propose a robust RBFN, β-RBFN, by applying the breakdown point approach in robust regression. Experimental results demonstrate the advantages of the proposed networks in robustness and simplicity over the plain RBFNs.

AB - Without considering spatial, stochastic, and temporal features inherent in natural neural systems, the computational power of conventional artificial neural networks (ANNs) is limited. In the present paper, we look at the stochastic complexity and construct a stochastic ANN by modeling stochastic fluctuations in the environmental stimuli such that all stimuli are prone to be corrupted by noise or even outliers and to break networks down; therefore, a positive-breakdown network is required. We investigate the stochasticity in the domain of function approximation (estimation) in the framework of radial basis function networks (RBFNs) and propose a robust RBFN, β-RBFN, by applying the breakdown point approach in robust regression. Experimental results demonstrate the advantages of the proposed networks in robustness and simplicity over the plain RBFNs.

UR - http://www.scopus.com/inward/record.url?scp=0029749563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029749563&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029749563

SP - 19

EP - 24

ER -

Li ST, Leiss EL. Constructing stochastic networks via β-RBF networks. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .