具时滞离散和分布BAM神经网络的全局渐近稳定性  

Globally asymptotic stability of BAM networks with discrete and distributed delays

作　　者：丁丹军[1,2] 

机构地区：[1]扬州大学数学科学学院,江苏扬州225002 [2]连云港师范高等专科学校数学系,江苏连云港222006

出　　处：《扬州大学学报（自然科学版）》2009年第4期1-5,共5页Journal of Yangzhou University：Natural Science Edition

基　　金：江苏省高校自然科学基金资助项目(06KJD110206)

摘　　要：研究一类同时具离散时滞和分布时滞的BAM(bidirectional associative memory)神经网络平衡点的全局渐近稳定性问题.所给BAM模型对激活函数做了扇形非线性条件假设,利用M矩阵理论,通过构造新的Lyapunov函数并利用一些分析技巧,获得具时滞离散和分布BAM神经网络的全局渐近稳定性的充分条件.数值例子说明了所得结果的有效性.This paper is concerned with the globally asymptotic stability of BAM （bidirectional associative memory） networks both with the discrete and the distributed time-delays. For the model of BAM networks, some hypothesis of sector nonlinear condition on activation functions are proposed. By employing the theory of M-matrix method, constructing a new Lyapunov-Krasovskii function and developing some stochastic analysis techniques, sufficient conditions are established for the BAM networks both with the discrete and the distributed time-delays to be globally asymptotically stable. A simple example is provided to demonstrate the effectiveness of the obtained sufficient condition.

关 键 词：BAM神经网络 离散时滞 分布时滞 全局渐近稳定性 LYAPUNOV-KRASOVSKII函数 

分 类 号：O175.14[理学—数学]