FAST LEARNING ALGORITHM OF WAVELET NEURAL NETWORKS AND ITS APPLICATION

In this paper we propose a fast learning algorithm of wavelet neural networks based on the least squares.Compared with existing similar algorithms,the present algorithm does not require any matrix computation and has the advantages of rapid convergence and low computational cost,which are beneficial to improve the real time property of wavelet networks.The algorithm is derived in this paper and the simulation results of several typical functions approximation show the effectiveness of the algorithm.