Anti-Synchronization of a Class of Delayed Chaotic Neural Networks Via State or Non-State Coupling

Based on an invariance principle of differential equations, an anti-synchronization method of a class of delayed chaotic neural networks is developed. This anti-synchronization method employs a much smaller feedback strength compared to some known results, and can be achieved without prior knowledge of the connection matrices. Moreover, it is robust against the effect of noise and multi-parameter mismatch. The state and non-state coupling in delayed chaotic neural networks are rigorously analyzed. Some numerical simulations are given to demonstrate the validity of the proposed method.