基于遗传算法的一类神经网络传递函数优化方法

2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628) Pub Date : 2002-11-07 DOI:10.1109/ICDSP.2002.1028345

M. Beddoes, R. Ward

{"title":"基于遗传算法的一类神经网络传递函数优化方法","authors":"M. Beddoes, R. Ward","doi":"10.1109/ICDSP.2002.1028345","DOIUrl":null,"url":null,"abstract":"This paper proposes a hybrid of two methods to determine the weight-constants in a class of artificial neuron networks, ANNs. The class of ANNs we are interested in are characterized by feed-forward processing elements. One of the methods is the genetic algorithm, GA; the other is \"training through\" back-propagation of the error, BPE. We expect our hybrid scheme to be faster than using BPE alone.","PeriodicalId":351073,"journal":{"name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A possible genetic-algorithm based method for optimizing a class of ANN transfer functions\",\"authors\":\"M. Beddoes, R. Ward\",\"doi\":\"10.1109/ICDSP.2002.1028345\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a hybrid of two methods to determine the weight-constants in a class of artificial neuron networks, ANNs. The class of ANNs we are interested in are characterized by feed-forward processing elements. One of the methods is the genetic algorithm, GA; the other is \\\"training through\\\" back-propagation of the error, BPE. We expect our hybrid scheme to be faster than using BPE alone.\",\"PeriodicalId\":351073,\"journal\":{\"name\":\"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICDSP.2002.1028345\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDSP.2002.1028345","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

本文提出了一种混合的两种方法来确定一类人工神经元网络的权重常数。我们感兴趣的一类人工神经网络具有前馈处理元素的特征。其中一种方法是遗传算法(GA);另一种是通过误差的反向传播(BPE)进行“训练”。我们希望我们的混合方案比单独使用BPE更快。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

A possible genetic-algorithm based method for optimizing a class of ANN transfer functions

This paper proposes a hybrid of two methods to determine the weight-constants in a class of artificial neuron networks, ANNs. The class of ANNs we are interested in are characterized by feed-forward processing elements. One of the methods is the genetic algorithm, GA; the other is "training through" back-propagation of the error, BPE. We expect our hybrid scheme to be faster than using BPE alone.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)

自引率

0.00%

发文量