Synchronizing high-dimensional chaos by an artificial neural network

A method for synchronizing high-dimensional chaos in experimental systems is devised by exploiting the learning and predicting capabilities of an artificial neural network (ANN). This method can be regarded as an extension of the methods developed by us for synchronizing and controlling chaos. The algorithm of the method identifies a “master” state variable of a chaotic system and perturbs an accessible parameter of the system to control this variable. The effectiveness of the method has been demonstrated with an example of the discrete predator-prey model