变时滞随机递归神经网络的全局指数稳定性

Global Exponential Stability of Stochastic Recurrent Neural Networks with Time-varying Delays

利用自由权值矩阵和不等式分析技巧,研究了一类随机变时滞神经网络的全局指数稳定性问题.该模型中考虑了神经网络的外部随机扰动因素,更加接近真实网络.通过构造适当的Lyapunov-Krasovskii泛函,以线性矩阵不等式形式给出了的全局指数稳定性判据,能够利用Matlab的LMI工具箱很容易地进行检验.此外,仿真结果进一步证明了结论的有效性.

By free-weighting matrix and combining the method of inequality analysis, the problem of stochastic exponential stability of a class of stochastic neural networks with time-varying delays is investigated. The external stochastic perturbations are unavoidable to be considered in neural networks. The time-delay factors are unknown and time-varying with known bounds. Based on Lyapunov-Krasovskii functional and stochastic analysis approaches, a new stability criterion is presented in terms of linear matrix inequalities （LMIs） to guarantee the delayed neural network to be exponentially stochastically stable. A numerical example is given to illustrate the usefulness of the proposed exponential stability criterion.