Global asymptotic stability of hybrid bidirectional associative memory neural networks with time delays


Arik S.

PHYSICS LETTERS A, vol.351, pp.85-91, 2006 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 351
  • Publication Date: 2006
  • Doi Number: 10.1016/j.physleta.2005.10.059
  • Journal Name: PHYSICS LETTERS A
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.85-91
  • Istanbul University Affiliated: Yes

Abstract

This Letter presents a sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with distributed time delays. The results impose constraint conditions on the network parameters of neural system independently of the delay parameter, and they are applicable to all bounded continuous non-monotonic neuron activation functions. The results are also compared with the previous results derived in the literature. (c) 2005 Elsevier B.V. All rights reserved.