Evollving Wavelet Neural Networks
Susu Yao, Chengjian Wei, Zhenya He · 1995
A wavelet izettral network isith evoli,itionary programming is proposed in this paper. Unlike conventional back propagation training algorithin, the evolutionary programming does not require gradient information and can provide a stochastic optiiiial search. The proposed method is used to approximate non-linear firnctions and solve classification pmblern. Soine experimental results are presented to show the potential of the evolving wavelet iiezrral netwoi-lzs