Global stability analysis of neural networks with multiple time varying delays

ENSARI T., Arik S.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, vol.50, no.11, pp.1781-1785, 2005 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 50 Issue: 11
  • Publication Date: 2005
  • Doi Number: 10.1109/tac.2005.858634
  • Journal Name: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1781-1785
  • Istanbul University Affiliated: Yes

Abstract

In this note, we study the equilibrium and stability properties of neural networks with time varying delays. Our main results give sufficient conditions for the existence, uniqueness and global asymptotic stability of the equilibrium point. The proposed conditions establish the relationships between network parameters of the neural systems and the delay parameters. The obtained results are applicable to all continuous nonmonotonic neuron activation functions and do not require the interconnection matrices to be symmetric. Some examples are also presented to compare our results with the previous results derived in the literature.