An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays

被引:107
作者
Shen, Yi [1 ]
Wang, Jun [2 ]
机构
[1] Huazhong Univ Sci & Technol, Key Lab Minist Educ Image Proc & Intelligent Cont, Wuhan 430074, Hubei, Peoples R China
[2] Chinese Univ Hong Kong, Dept Mech & Automat Engn, Shatin, New Territories, Peoples R China
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2008年 / 19卷 / 03期
关键词
global exponential stability; M-matrix; recurrent neural networks; time-varying delays;
D O I
10.1109/TNN.2007.911751
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This brief paper presents an M-matrix-based algebraic criterion for the global exponential stability of a class of recurrent neural networks with decreasing time-varying delays. The criterion improves some previous criteria based on M-matrix and is easy to be verified with the connection weights of the recurrent neural networks with decreasing time-varying delays. In addition, the rate of exponential convergence can be estimated via a simple computation based on the criterion herein.
引用
收藏
页码:528 / 531
页数:4
相关论文
共 20 条