Global exponential stability and periodic solutions of recurrent neural networks with delays

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

147 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)393-404
Journal / PublicationPhysics Letters, Section A: General, Atomic and Solid State Physics
Volume298
Issue number5-6
Publication statusPublished - 17 Jun 2002
Externally publishedYes

Abstract

In this Letter, by utilizing the Lyapunov functional method, applying M-matrix and topological degree theory, we analyze the global exponential stability and the existence of periodic solutions of a class of recurrent neural networks with delays. Some simple and new sufficient conditions ensuring existence, uniqueness and global exponential stability of the equilibrium point and periodic solutions of delayed recurrent neural networks are obtained, which do not require the activation functions to be differentiable, bounded and monotone nondecreasing. In addition, two examples are also given to illustrate the theory. © 2002 Elsevier Science B.V. All rights reserved.

Research Area(s)

  • Delays, Global exponential stability, Lyapunov function, M-matrix, Periodic solutions, Recurrent neural networks, Topological degree