Stability analysis of recurrent neural networks with piecewise constant argument of generalized type


AKHMET M., ARUĞASLAN ÇİNÇİN D., YILMAZ E.

NEURAL NETWORKS, vol.23, no.7, pp.805-811, 2010 (Peer-Reviewed Journal) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 23 Issue: 7
  • Publication Date: 2010
  • Doi Number: 10.1016/j.neunet.2010.05.006
  • Journal Name: NEURAL NETWORKS
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.805-811
  • Keywords: Neural networks, Piecewise constant argument of generalized type, Method of Lyapunov functions, GLOBAL EXPONENTIAL STABILITY, TIME-VARYING DELAYS, DIFFERENTIAL-EQUATIONS, ASYMPTOTIC STABILITY, PERIODIC-SOLUTIONS, TRAVELING-WAVES

Abstract

In this paper, we apply the method of Lyapunov functions for differential equations with piecewise constant argument of generalized type to a model of recurrent neural networks (RNNs). The model involves both advanced and delayed arguments. Sufficient conditions are obtained for global exponential stability of the equilibrium point. Examples with numerical simulations are presented to illustrate the results. (C) 2010 Elsevier Ltd. All rights reserved.