Optimal chaotic synchronization of stochastic delayed recurrent neural networks

This paper presents a theoretical design of how an optimal synchronization is achieved for stochastic delayed recurrent neural networks. According to the concept of drive-response, a control method is developed to guarantee that the chaotic drive network synchronizes with the chaotic response network influenced by uncertain noise signals. The formulation of a nonlinear optimal control law is rigorously derived by using Lyapunov technique and solving a Hamilton-Jacobi-Bellman (HJB) equation. To verify the analytical results, a numerical example is given to demonstrate the effectiveness of the proposed approach, which is simple and easy to implement in reality.