一种小波神经网络的快速学习算法及其应用

FAST LEARNING ALGORITHM OF WAVELET NEURAL NETWORKS AND ITS APPLICATION

提出一种基于最小二乘的小波神经网络的快速学习算法 ,与现有的同类算法相比 ,该算法无需任何矩阵运算 ,兼有快速收敛和计算量较小的特点 ,有助于提高小波网络的实时性能 .推导了算法 ,几个典型的函数逼近的仿真实例表明了算法的优良性能 .

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.