Robust stability of stochastic delayed additive neural networks with Markovian switching

He Huang, Daniel W.C. Ho, Yuzhong Qu

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

72 Citations (Scopus)

Abstract

This paper is concerned with the problem of robust stability for stochastic interval delayed additive neural networks (SIDANN) with Markovian switching. The time delay is assumed to be time-varying. In such neural networks, the features of stochastic systems, interval systems, time-varying delay systems and Markovian switching are taken into account. The mathematical model of this kind of neural networks is first proposed. Secondly, the global exponential stability in the mean square is studied for the SIDANN with Markovian switching. Based on the Lyapunov method, several stability conditions are presented, which can be expressed in terms of linear matrix inequalities. As a subsequent result, the stochastic interval additive neural networks with time-varying delay are also discussed. A sufficient condition is given to determine its stability. Finally, two simulation examples are provided to illustrate the effectiveness of the results developed. © 2007 Elsevier Ltd. All rights reserved.
Original languageEnglish
Pages (from-to)799-809
JournalNeural Networks
Volume20
Issue number7
DOIs
Publication statusPublished - Sept 2007

Research Keywords

  • Additive neural networks
  • Global exponential stability
  • Interval systems
  • Markov chain
  • Stochastic systems
  • Time-varying delay systems

Fingerprint

Dive into the research topics of 'Robust stability of stochastic delayed additive neural networks with Markovian switching'. Together they form a unique fingerprint.

Cite this