具有变时滞的离散双向联想记忆神经网络的全局指数稳定性

利用Lyapunov函数和线性矩阵不等式(LMI),给出了判定一类双向联想记忆(BAM)神经网络模型的指数稳定的充分性条件.该条件去掉了以往论文中所要求的激活函数单调,可微分的条件,而且所得结果利用里的工具易于检测.并举例说明本文结果的有效性.

Globally Exponential Stability of Discrete-time Bi-directional Associative Memory Networks with Time-varying Delays

In this letter, by employing a Lyapunov-Krasovskii function and linear matrix inequality (LMI), we derive a globally exponentially stabile sufficient condition for discrete-time ABM neural networks with variable delays. The activation funtions are assumed to be neither strict monotonic nor differentiable. The feasibility of such an LMI can be easily checked by using the numerically efficient Matlab LMI Toolbox. A numerical example is illustrated to show the effectiveness of our result.