Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (6): 30-32.

• 研究、探讨 • Previous Articles     Next Articles

Global asymptotic stability of a class of neutral neural networks with time delays

LUO Ricai1, XU Honglei2,3   

  1. 1.Department of Mathematics, Hechi University, Yizhou, Guangxi 546300, China
    2.School of Information Science and Engineering, Central South University, Changsha 410083, China
    3.Department of Mathematics and Statistics, Curtin University, Perth, WA, Australia
  • Received:1900-01-01 Revised:1900-01-01 Online:2012-02-21 Published:2012-02-21

一类中立型时滞神经网络的全局渐近稳定性

罗日才1,许弘雷2,3   

  1. 1.河池学院 计算机与信息科学系,广西 宜州 546300
    2.中南大学 信息科学与工程学院,长沙 410083
    3.澳大利亚科廷大学 数学与统计系 澳大利亚

Abstract: This paper discusses the stability problem of a class of neutral neural networks with time delays. By constructing Lyapunov-Krasovskii-type functional, and using Schur complement matrix properties, it studies the global asymptotic stability of these kinds of delayed neutral neural networks and obtains sufficient conditions of the asymptotic stability based on matrix eigenvalues. Some sufficient conditions, expressed in the form of matrix eigenvalues, of global asymptotic stability for Hopfield neural networks with time delays are obtained as well. The numerical simulations test the validity of the results.

Key words: delayed neural networks, neutral, Schur complement, global asymptotic stability

摘要: 讨论了一类带有时滞的中立型神经网络的稳定性问题。通过构造Lyapunov-Krasovskii泛函,利用矩阵Schur补性质研究了此类中立型时滞神经网络模型的全局渐近稳定性,得出基于矩阵特征值的稳定性的充分判据,并给出基于矩阵特征值的时滞Hopfield神经网络全局渐近稳定性的充分条件;数值仿真检验了结果的有效性。

关键词: 时滞神经网络, 中立型, Schur补, 全局渐近稳定性