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. In this paper, we study the global exponential stability of a class of neutral neural networks with time-varying delays. By constructing Lyapunov-Krasovskii functional and using the method of linear matrix inequalities, we establish a new sufficient condition for the global exponential stability of delayed neural networks The conditions are expressed in terms of linear matrix inequalities.Furthermore, a new criterion for robust global exponential stability for a class of uncertain neutral neutral neural networks is given.