A New Sufficient Condition for Global Robust Stability of Delayed Neural Networks

Ozcan N.

NEURAL PROCESSING LETTERS, vol.34, no.3, pp.305-316, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 34 Issue: 3
  • Publication Date: 2011
  • Doi Number: 10.1007/s11063-011-9194-9
  • Journal Name: NEURAL PROCESSING LETTERS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.305-316
  • Bursa Uludag University Affiliated: No

Abstract

In this paper, by using Lyapunov stability theorems, we present a new sufficient condition for the existence, uniqueness and global robust asymptotic stability of the equilibrium point for delayed neural networks. This condition basically establishes a relationship between the network parameters of the neural system. The obtained condition can be easily verified as it is in terms of the network parameters only. Some illustrative numerical examples are also given to compare our result with the previous robust stability results derived in the literature.