有脉冲和时滞的双向记忆神经网络稳定性分析  

Stability analysis of generalized bidirectional associative memory neural networks with impulse and time delays

作　　者：张忠[1] 吕建斌[1] 李传东[1] 

机构地区：[1]重庆大学计算机学院,重庆400030

出　　处：《重庆大学学报（自然科学版）》2008年第7期770-774,780,共6页Journal of Chongqing University

基　　金：国家自然科学基金资助项目(60574024);博士后科学基金资助项目(20060400196)

摘　　要：利用Lyapunov函数和二维Hanalay类型不等式,研究带有脉冲和时延的广义双向联想记忆神经网络平衡点的全局指数稳定性,得到了几个判断网络全局指数稳定的充分条件,这些条件刻画了脉冲强度和没有脉冲的连续子网络(双向联想记忆神经网络的连续部分)的指数收敛速度对整个网络的全局指数稳定性的混合影响。研究结果表明即使脉冲对网络状态有放大的影响,脉冲时滞双向联想记忆神经网络也可能保持连续子网络的全局指数稳定性质。数值例子验证了理论结果的正确性。The global exponential stability of the equilibrium point of generalized delayed bidirectional associative memory （DBAM） neural networks with impulse effects was studied using the Lyapunov function and a 2-D Hanalay-type inequality. Several results characterized the aggregated effects of impulses and the dynamic properties of the impulse-free DBAM on the exponential stability of the DBAM under consideration. It is shown that impulsive DBAM will preserve the global exponential stability of the impulse-free DBAM even if the impulses have enlarging effects on the states of neurons. The effectiveness of the theoretical results was validated by a numerical example.

关 键 词：时滞双向联想记忆神经网络 脉冲 指数稳定 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]