一类具有混合时滞的神经网络指数稳定性分析

Exponential stability analysis for a class of neural networks with mixed delays

讨论了一类具有混合时滞(包含离散和分布时滞)的人工神经网络的指数稳定性问题.通过将时滞区间分为不等的两部分,并结合倒数凸方法,得到了系统指数稳定的新判据,判据以线性矩阵不等式的形式给出.最后用两个数值实例说明了所得结论的有效性与更小的保守性.

The problem of exponential stability analysis for artificial neural networks with mixed delays （including discrete and distributed time-varying delays）is discussed.By dividing the delay interval into two unequal subintervals and using the reciprocal convex approach,an improved delay-dependent exponential-stability criterion is derived in terms of the linear matrix inequalities （LMIs）. Finally, numerical examples illustrate the effectiveness and less conservatism of the obtained conditions.