Global exponential stability of Hopfield neural networks with delays and inverse Lipschitz neuron activations

被引:26
|
作者
Wu, Huaiqin [1 ]
机构
[1] Yanshan Univ, Dept Appl Math, Qinhuangdao 066001, Peoples R China
基金
中国国家自然科学基金;
关键词
Neural networks; Global exponential stability; Neuron activation functions; Inverse Lipschitz functions; Topological degree; Matrix inequality; TIME;
D O I
10.1016/j.nonrwa.2008.04.016
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper introduces a new class of functions called inverse Lipschitz functions (IL). By using IL, a novel class of neural networks with inverse Lipschitz neuron activation functions is presented. By the topological degree theory and matrix inequality techniques, the existence and uniqueness of equilibrium point for the neural network are investigated. By constructing appropriate Lyapunov functions, a sufficient condition ensuring global exponential stability of the neural network is given. At last, two numerical examples are given to demonstrate the effectiveness of the results obtained in this paper. (C) 2008 Elsevier Ltd. All rights reserved.
引用
收藏
页码:2297 / 2306
页数:10
相关论文
共 50 条