Equilibrium and stability analysis of delayed neural networks under parameter uncertainties

Faydasicok O., Arik S.

APPLIED MATHEMATICS AND COMPUTATION, vol.218, no.12, pp.6716-6726, 2012 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 218 Issue: 12
  • Publication Date: 2012
  • Doi Number: 10.1016/j.amc.2011.12.036
  • Journal Name: APPLIED MATHEMATICS AND COMPUTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.6716-6726
  • Keywords: Stability analysis, Delayed neural networks, Interval matrices, Lyapunov functionals, GLOBAL ROBUST STABILITY, EXPONENTIAL STABILITY, DISTRIBUTED DELAYS, DISCRETE, CRITERIA
  • Istanbul University Affiliated: Yes

Abstract

This paper proposes new results for the existence, uniqueness and global asymptotic stability of the equilibrium point for neural networks with multiple time delays under parameter uncertainties. By using Lyapunov stability theorem and applying homeomorphism mapping theorem, new delay-independent stability criteria are obtained. The obtained results are in terms of network parameters of the neural system only and therefore they can be easily checked. We also present some illustrative numerical examples to demonstrate that our result are new and improve corresponding results derived in the previous literature. (C) 2011 Elsevier Inc. All rights reserved.