上海交通大学学报(自然版) ›› 2011, Vol. 45 ›› Issue (08): 1151-1157.

• 自动化技术、计算机技术 • 上一篇    下一篇

随机中立型时滞神经网络的全局渐近稳定性判据

 刘国权1, 杨先一1, 柴毅1, 付伟1, 冯伟2, 时光1   

  1. (1.重庆大学 自动化学院, 重庆 400044; 2.重庆教育学院 计算机系, 重庆 400067)
  • 收稿日期:2011-03-07 出版日期:2011-08-30 发布日期:2011-08-30
  • 基金资助:

    国家自然科学基金(60974090),中央高校基本科研业务费科研专项基金(CDJXS11172237),重庆市自然科学基金(2009BB2378)资助项目

Global Asymptotic Stability Criteria for Stochastic Neutral-Type Delayed Neural Networks

 LIU  Guo-Quan-1, YANG  Xian-Yi-1, CHAI  Yi-1, FU  Wei-1, FENG  Wei-2, SHI  Guang-1   

  1. (1.College of Automation, Chongqing University, Chongqing 400044, China;2.Department of Computer, Chongqing Education College, Chongqing 400067, China)
  • Received:2011-03-07 Online:2011-08-30 Published:2011-08-30

摘要: 研究一类含有变时滞的随机中立型神经网络的全局渐近稳定性问题.通过构造一个新的LyapunovKrasovskii泛函和不等式技术,得到了基于线性矩阵不等式表示的与时滞大小有关的时滞稳定的充分判据.该判据考虑了一类含有分布式时滞和随机扰动项并且激活函数是常量(正数、负数和零)的中立型神经网络,与现有文献相比,其更具有一般性和较少保守性.最后,通过2个算例分析,验证了所得结果是有效的.

关键词:  , 全局渐近稳定性, 随机扰动, 神经网络, 线性矩阵不等式, 变时滞

Abstract:  The problem of global asymptotic stability analysis for a class of stochastic neutral-type neural networks with variable delays was investigated. By constructing an appropriate Lyapunov functional combined with inequality technique,sufficient stability criteria dependent on the size of the time delay were obtained in terms of linear matrix inequality (LMI). A class of neutral-type networks considered in the paper consists of distributed delays, stochastic perturbation and activation functions which are assumed to be constants (positive, negative, and zero), so these proposed criteria are universal and representative. The proposed stability results are more universal and less conservative than the existing ones.  Finally, two numerical examples were given to demonstrate the effectiveness of the proposed results.

Key words:  global asymptotic stability, stochastic perturbation, neural networks, linear matrix inequality (LMI), variable delays

中图分类号: