The application of wavelet neural network in time series prediction and system modeling based on multiresolution learning

In this paper, a new kind of wavelet neural networks (WNN) was proposed, the performance was compared with multilayer perceptron (MLP) in the application of chaotic time series single and multiple step prediction based on an improved multiresolution learning paradigm. The experimental results demonstrated the great approximation ability of WNN and its suitability in prediction and system modeling.