东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2006, Vol. 27 ›› Issue (2): 123-126.DOI: -

• 论著 • 上一篇    下一篇

一类延迟神经网络的全局渐近稳定性

王占山;张化光;吕化;   

  1. 东北大学信息科学与工程学院;东北大学信息科学与工程学院;东北大学信息科学与工程学院 辽宁沈阳110004;辽宁沈阳110004;辽宁沈阳110004
  • 收稿日期:2013-06-23 修回日期:2013-06-23 出版日期:2006-02-15 发布日期:2013-06-23
  • 通讯作者: Wang, Z.-S.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(60244017,60325311)

Global asymptotic stability of a class of delayed neural networks

Wang, Zhan-Shan (1); Zhang, Hua-Guang (1); Lu, Hua (1)   

  1. (1) School of Information Science and Engineering, Northeastern University, Shenyang 110004, China
  • Received:2013-06-23 Revised:2013-06-23 Online:2006-02-15 Published:2013-06-23
  • Contact: Wang, Z.-S.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

943

摘要： 针对一类能够由中立型变延迟非线性微分方程描述的神经网络模型,通过构造一个Lyapunov-Krasovskii泛函,给出了平衡点惟一性和全局渐近稳定的充分条件.所得到的稳定判据不依赖于时间延迟大小,不要求神经元激励函数的有界性、严格单调性和可微性,只与连接矩阵和延迟的导数项有关,且该稳定判据能够表示成线性矩阵不等式形式,易于求解验证.

关键词: 延迟神经网络, 中立型, 全局渐近稳定, 线性矩阵不等式, 时变延迟

Abstract: A new sufficient condition is given to provide the uniqueness and global asymptotic stability of the equilibrium point for a class of delayed neural network models of neutral type by constructing a Lyapunov-Krasovskii functional without assuming the boundedness, strict monotonicity and differentiability of neuron excitation function. This stability criterion imposes constraints on the interconnected matrices and derivative of time delays and is independent of the amplitude of time delays, which can be conveniently expressed in the form of linear matrix inequality (LMI) and easy to check.

中图分类号: