journal6 ›› 2008, Vol. 29 ›› Issue (4): 30-34.

• Mathematics • Previous Articles     Next Articles

Exponential Stability of Neural Networks with Time Delays


  1. (Department of Mathematics and Computer Science,Chongqing Normal University,Chongqing 400047,China)
  • Online:2008-07-25 Published:2012-05-21
  • About author:YANG De-gang (1976-),male,was born in Zigong City,Sichuan Province,associate professor of Chongqing Normal University;research areas are neural networks,nonlinear dynamical systems and network security.
  • Supported by:

    Supported by the NSFC (60573047);Natural Science Foundation Project of CQ CSTC (2006BB2254,2007BB2231);Applying Basic Research Program of Chongqing Education Committee (KJ060818);Doctoral Foundation Project of Chongqing Normal University (08XLB003)

Abstract: This paper considers the problems of global exponential stability for a general class of neural networks with time delays,a new criterion ensuring global exponential stability is obtained by utilizing Razumikhin theorem and the linear matrix inequality (LMI) technique.Distinct difference from other analytical approaches lies in “linearization” of the neural network model,by which the considered neural network model is transformed into a linear time-variant system.The obtained conditions show to be less conservative and restrictive.A numerical simulation is given to illustrate the validity of our results.

Key words: neural networks, time delays, exponential stability, linear matrix inequality, Razumikhin theorem

WeChat e-book chaoxing Mobile QQ