Design of the scaling-wavelet neural network using genetic algorithm

In this paper, we propose the composition method of the activation function in the hidden layer with the scaling function which can represent the region where the several wavelet functions can represent. In this method, we can decrease the size of the network with a few wavelet functions. In addition to, when we determine the parameters of the scaling function we can process rough approximation and then the network becomes more stable. The other wavelets can be determined by the global solution, the genetic algorithm which is suitable for the suggested problem and also, we use the back-propagation algorithm in the learning of the weights. In this step, we approximate the target function with fine tuning level. The complex neural network suggested in this paper is a new structure and important simultaneously in the point of handling the determination problem in the wavelet initialization.