Almost periodic solutions of recurrent neural networks with continuously distributed delays

被引:47
|
作者
Xiang, Hongjun [1 ,2 ]
Cao, Jinde [1 ]
机构
[1] Southeast Univ, Dept Math, Nanjing 210096, Peoples R China
[2] Xiangnan Univ, Dept Math, Chenzhou 423000, Peoples R China
基金
中国国家自然科学基金; 美国国家科学基金会;
关键词
Recurrent neural networks; Almost periodic solution; Distributed delay; Lyapunov functional; GLOBAL EXPONENTIAL STABILITY; VARIABLE-COEFFICIENTS; EXISTENCE; ATTRACTIVITY; TEMPLATES; TIME;
D O I
10.1016/j.na.2009.05.079
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
In this paper, a class of recurrent neural networks with continuously distributed delays is discussed. Without resorting to the theory of exponential dichotomy, several new sufficient conditions are obtained ensuring the existence of an almost periodic solution for this model based on a special functional and analysis technique. Moreover, by constructing suitable Lyapunov functions, the attractivity, and exponential stability of the almost periodic solution are also considered for the system. The results obtained are helpful to design globally stable almost periodic oscillatory neural networks. A numerical example is given to show the feasibility of the results obtained. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:6097 / 6108
页数:12
相关论文
共 50 条