A neural network as a predictor of the discrete map

The possibility of predicting the regular and chaotic dynamics of a discrete map by using artificial neural network is studied. The method of error back-propagation is used for calculation the coefficients of the multilayer network. The predicting properties of the neural network are explored in a wide region of the system parameter for both regular and chaotic behaviors. The dependance of the prediction accuracy from the degree of chaos and from the number of layers of the network is studied.