{"title":"Fast convergence algorithm for wavelet neural network used for signal or function approximation","authors":"Song Xiangyu, Qi Feihu","doi":"10.1109/ICSIGP.1996.566584","DOIUrl":null,"url":null,"abstract":"A new way to set the initial values of the wavelet neural network's parameters is proposed in order to improve the convergence speed. Experiments on linear polynomials, exponent functions, sin & cos functions and a certain multistage simulation function show the neural network has a much faster convergence speed and can be widely used for approximating many kinds of signals and functions. A discussion on the merit of this method is given. The experiment results are satisfactory.","PeriodicalId":385432,"journal":{"name":"Proceedings of Third International Conference on Signal Processing (ICSP'96)","volume":"41 18","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of Third International Conference on Signal Processing (ICSP'96)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSIGP.1996.566584","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
A new way to set the initial values of the wavelet neural network's parameters is proposed in order to improve the convergence speed. Experiments on linear polynomials, exponent functions, sin & cos functions and a certain multistage simulation function show the neural network has a much faster convergence speed and can be widely used for approximating many kinds of signals and functions. A discussion on the merit of this method is given. The experiment results are satisfactory.