小波网络

Wavelet networks.

作者信息

Zhang Q, Benveniste A

机构信息

Linkopings Tekniska Hogskola.

出版信息

IEEE Trans Neural Netw. 1992;3(6):889-98. doi: 10.1109/72.165591.

DOI:10.1109/72.165591

PMID:18276486

Abstract

A wavelet network concept, which is based on wavelet transform theory, is proposed as an alternative to feedforward neural networks for approximating arbitrary nonlinear functions. The basic idea is to replace the neurons by ;wavelons', i.e., computing units obtained by cascading an affine transform and a multidimensional wavelet. Then these affine transforms and the synaptic weights must be identified from possibly noise corrupted input/output data. An algorithm of backpropagation type is proposed for wavelet network training, and experimental results are reported.

摘要

提出了一种基于小波变换理论的小波网络概念，作为前馈神经网络的替代方案，用于逼近任意非线性函数。其基本思想是用“小波元”取代神经元，即通过级联仿射变换和多维小波得到的计算单元。然后必须从可能被噪声污染的输入/输出数据中识别出这些仿射变换和突触权重。提出了一种用于小波网络训练的反向传播型算法，并报告了实验结果。