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

  • Authors:
  • Sabri Arik;Vedat Tavsanoglu

  • Affiliations:
  • Department of Computer Engineering, Istanbul University, 34320 Avcilar, Turkey;Department of Electronics, Yildiz Technical University, Besiktas, Turkey

  • Venue:
  • Neurocomputing
  • Year:
  • 2005

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper presents a sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with fixed time delays. The results impose constraint conditions on the network parameters of neural system independent of the delay parameters. The results are applicable to all continuous non-monotonic neuron activation functions. The results are also compared with the previously reported results in the literature, implying that the results obtained in this paper provide one more set of criteria for determining the stability of bidirectional associative memory neural networks with time delays.