On stochastic stability of dynamic neural models in presence of noise

K Najarian

doi:10.3934/proc.2003.2003.656

Article Contents

2003, Volume 2003: 656-663. Doi: 10.3934/proc.2003.2003.656 open access

This issue Previous Article Existence of square integrable solutions of perturbed nonlinear differential equations Next Article Dynamics of principal configurations near umbilics for surfaces in $mathbb(R)^4$

On stochastic stability of dynamic neural models in presence of noise

K Najarian¹

1.
College of Information Technology The University of North Carolina at Charlotte, 9201 University City Blvd, Charlotte, NC 28223

Received: August 31, 2002

Revised: February 28, 2003

Published: March 2003

Abstract Related Papers Cited by

Abstract

Dynamic feedback neural networks are known to present powerful tools in modeling of complex dynamic models. Since in many real applications, the stability of such models (specially in presence of noise) is of great importance, it is essential to address stochastic stability of such models. In this paper, sufficient conditions for stochastic stability of two families of feedback sigmoid neural networks are presented. These conditions are set on the weights of the networks and can be easily tested.

Keywords:

Mathematics Subject Classification: Primary: 58F15, 58F17, 58F11; Secondary: 53C35.

Citation:

Article Metrics

HTML views() PDF downloads(41) Cited by(0)

On stochastic stability of dynamic neural models in presence of noise

Abstract

Access History

Article Metrics

Access History

Other Articles By Authors

Catalog

On stochastic stability of dynamic neural models in presence of noise

Abstract

Access History

SHARE

Article Metrics

Access History

Other Articles By Authors

Catalog

Export File

Citation

Format

Content