Nonlinear Time Series PredictionUsing Chaotic Neural Networks

A nonlinear feedback term is introduced into the evaluation equationof weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting,we use the model to forecast the nonlinear time series which is producedby Makey-Glass equation. By selecting the suitable feedback term, thesystem can escape from the local minima and converge to the global minimumor its approximate solutions, and the forecasting results are better thanthose of backpropagation algorithm.