计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (19): 48-50.DOI: 10.3778/j.issn.1002-8331.2010.19.013

• 研究、探讨 • 上一篇    下一篇

区间时滞神经网络的随机稳定性

吴海霞1,2,冯伟2,张伟2   

  1. 1.重庆大学计算机学院,重庆400044
    2.重庆教育学院计算机与现代教育技术系,重庆400067
  • 收稿日期:2009-01-05 修回日期:2009-02-16 出版日期:2010-07-01 发布日期:2010-07-01
  • 通讯作者: 吴海霞

Stochastic stability of neural networks with interval time-varying delays

WU Hai-xia1,2,FENG Wei2,ZHANG Wei2   

  1. 1.College of Computer Science,Chongqing University,Chongqing 400044,China
    2.Department of Computer and Modern Education Technology,Chongqing Education College,Chongqing 400067,China
  • Received:2009-01-05 Revised:2009-02-16 Online:2010-07-01 Published:2010-07-01
  • Contact: WU Hai-xia

摘要: 分析了区间变时滞的随机神经网络的全局渐进稳定性。区间变时滞不仅考虑了时变因素,而且考虑了时滞时变的上界和下界。通过Itô’s 微分公式和构造适当的李雅普罗夫泛函,并且引入自由权值矩阵,以线性矩阵不等式形式给出了该系统在均方意义下的全局渐进稳定的充分性判据。数值算例进一步证明了结论的有效性。

Abstract: By Itô’s differential formula and combining the method of inequality analysis,the problem of stochastic asymptotical stability of a class of stochastic neural networks with time-varying delays and parameter uncertainties is investigated.The time-delay factors are unknown and time-varying with known bounds.Based on Lyapunov-Krasovskii functional and stochastic
analysis approaches,some new stability criteria are presented in terms of linear matrix inequalities(LMIs) to guarantee the delayed neural network to be asymptotically stochastically asymptotically stable in the mean square for all admissible uncertainties.
Numerical examples are given to demonstrate the usefulness of the proposed asymptotical stability criteria.

中图分类号: