Mean-Square Asymptotic Synchronization Control of Discrete-Time Neural Networks With Restricted Disturbances and Missing Data

The problem of controller design is investigated to achieve the mean-square asymptotic synchronization of discrete-time neural networks with time-varying delay and restricted disturbances. The unreliable communication links between the neural networks, which are modeled as stochastic dropouts satisfying the Bernoulli distributions, are taken into account. By applying the Lyapunov function, a synchronization controller design method is proposed in the form of linear matrix inequalities. The design method is also extended to neural networks including modeling uncertainties. Two numerical examples are given to illustrate the effectiveness of the proposed methods.