Feedforward Wavelet Neural Network and Multi-variable Functional Approximation
暂无分享,去创建一个
In this paper, a novel WNN, multi-input and multi-output feedforward wavelet neural network is constructed. In the hidden layer, wavelet basis functions are used as activate function instead of the sigmoid function of feedforward network. The training formulas based on BP algorithm are mathematically derived and training algorithm is presented. A numerical experiment is given to validate the application of this wavelet neural network in multi-variable functional approximation.
[1] Ingrid Daubechies,et al. Ten Lectures on Wavelets , 1992 .
[2] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..
[3] Qinghua Zhang,et al. Wavelet networks , 1992, IEEE Trans. Neural Networks.
[4] Qinghua Zhang,et al. Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.