离散型随机BAM神经网络时滞分布依赖全局指数稳定性

研究一类具有随机时滞与随机干扰的离散型BAM神经网络的全局指数稳定性，所建模型同时考虑离散时滞变化区间与分布概率对稳定性的影响．通过构造新的Lyapunov泛函并结合线性矩阵不等式（LMI）方法，得到了均方意义下依赖于时滞分布的全局指数稳定性条件．

Delay-distribution-dependent Global Exponential Stability of Discrete-time Stochastic BAM Neural Networks

The global exponential stability for a class of discrete-time bidirectional associative memory （BAM） neural networks with randomly time-varying delays and stochastic disturbances is investigated. The effects on both variation range and probability distribution of time-varying de- lays are taken into account in the model. By employing a novel Lyapunov-Krasvskii functional and linear matrix inequality （LMI） approach, some delay-distribution-dependent criteria are achieved for the discrete-time stochastic BAM neural networks to be global exponential stability in the mean square.