带有时变时滞的中立型神经网络的鲁棒指数稳定性

ROBUST EXPONENTIAL STABILITY FOR NEUTRAL-TYPE NEURAL NETWORKS WITH TIME-VARYING DELAYS

研究一类带有时变时滞的中立型神经网络的全局指数稳定性问题.通过构造LyapunovKrasovskii泛函并使用线性矩阵不等式方法,建立了保障时滞神经网络全局指数稳定的新的时滞相关充分条件.这些条件用线性矩阵不等式表达.进一步,文章对一类不确定时滞中立型神经网络给出了鲁棒全局指数稳定的新判据.

The paper is concerned with global exponential stability for a class of neutral-type neural networks with time-varying delays. By constructing an appro-priate Lyapunov-Krasovskii functional and with the help of linear matrix inequality （LMI） approaches, some delay-dependent sufficient conditions to guarantee the glob-ally exponential stability of such systems are established in terms of the linear matrix inequality （LMI）. Furthermore, some novel criteria of robust globally exponential stability for a class of uncertain time-delay neutral-type neural networks are given.