On stochastic stability of dynamic neural models in presence of noise

Pages: 656 - 663, Issue Special, July 2003

 Abstract        Full Text (161.5K)              

K Najarian - College of Information Technology The University of North Carolina at Charlotte, 9201 University City Blvd, Charlotte, NC 28223, United States (email)

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:  Dynamic Neural Networks,Stochastic Stability, Nonlinear ARX Models.
Mathematics Subject Classification:  Primary: 58F15, 58F17, 58F11; Secondary: 53C35.

Received: September 2002;      Revised: March 2003;      Published: April 2003.