Synchronization of an uncertain chaotic system via recurrent neural networks

Incorporating distributed recurrent networks with high-order connections between neurons, the identification and synchronization problem of an unknown chaotic system in the presence of unmodelled dynamics is investigated. Based on the Lyapunov stability theory, the weights learning algorithm for the recurrent high-order neural network model is presented.Also, analytical results concerning the stability properties of the scheme are obtained. Then adaptive control law for eliminating synchronization error of uncertain chaotic plant is developed via Lyapunov methodology. The proposed scheme is applied to model and synchronize an unknown Rossler system.