Prediction of chaotic time series using recurrent neural networks

Abstract

The authors propose to train and use a recurrent artificial neural network (ANN) to predict a chaotic time series. Instead of training the network with the next sample in the time series as is normally done, a sequence of samples that follows the present sample will be utilized. Dynamical parameters extracted from the time series provide the information to set the length of these training sequences. The proposed method has been applied to predict both periodic and chaotic time series, and is superior to the conventional ANN approach.<>