利用-矩阵理论以及Halanay不等式技巧,给出了一类含有变时滞的非自治BAM(bi—directional associative memory)神经网络周期解的全局指数稳定性的充分条件,这些条件去掉了对激活函数的有界性、单调性和可微性的要求,且在某些情况下更易验证。最后通过一个例子验证了所给结果的有效性。
Applying the M-matrix theory, Halanay inequality technique and some analysis techniques, one sufficient condition is obtained for the global exponential stability of periodic solutions for non-autonomous BAM neural networks with time-varying delays.