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


Arik S., Tavsanoglu V.

NEUROCOMPUTING, cilt.68, ss.161-176, 2005 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 68
  • Basım Tarihi: 2005
  • Doi Numarası: 10.1016/j.neucom.2004.12.002
  • Dergi Adı: NEUROCOMPUTING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.161-176
  • İstanbul Üniversitesi Adresli: Evet

Özet

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. (c) 2005 Elsevier B.V. All rights reserved.