Evolving wavelet neural networks for function approximation
Shuai Yao, Cheok Jia Wei, Zhili He · Electronics Letters · 1996
A wavelet-based neural network with evolutionary programming is proposed. Unlike conventional backpropagation training algorithms, the evolutionary programming does not require gradient information and can provide a stochastic optimal search. Evolutionary programming is applied to optimise the wavelet neural network for function approximation. Experimental results are presented to show the potential of the evolutionary wavelet neural networks.