反向传播神经网络的基向量分析

[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems Pub Date : 1991-05-14 DOI:10.1109/MWSCAS.1991.252222

M.-S. Chen, M. Manry

{"title":"反向传播神经网络的基向量分析","authors":"M.-S. Chen, M. Manry","doi":"10.1109/MWSCAS.1991.252222","DOIUrl":null,"url":null,"abstract":"Develops a polynomial basis function approach for modeling BP (backpropagation) neural networks. This method leads directly to a constructive proof of the BP approximation theorem. In addition, the basis vector approach provides a means to synthesize the BP neural network output as a polynomial function. An algorithm for pruning the useless basis vectors is also demonstrated.<<ETX>>","PeriodicalId":6453,"journal":{"name":"[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems","volume":"171 1","pages":"23-26 vol.1"},"PeriodicalIF":0.0000,"publicationDate":"1991-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Basis vector analyses of back-propagation neural networks\",\"authors\":\"M.-S. Chen, M. Manry\",\"doi\":\"10.1109/MWSCAS.1991.252222\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Develops a polynomial basis function approach for modeling BP (backpropagation) neural networks. This method leads directly to a constructive proof of the BP approximation theorem. In addition, the basis vector approach provides a means to synthesize the BP neural network output as a polynomial function. An algorithm for pruning the useless basis vectors is also demonstrated.<<ETX>>\",\"PeriodicalId\":6453,\"journal\":{\"name\":\"[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems\",\"volume\":\"171 1\",\"pages\":\"23-26 vol.1\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1991-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MWSCAS.1991.252222\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MWSCAS.1991.252222","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

摘要

提出了一种基于多项式基函数的BP(反向传播)神经网络建模方法。这种方法直接给出了BP近似定理的构造性证明。此外，基向量方法提供了一种将BP神经网络输出合成为多项式函数的方法。本文还演示了一种对无用基向量进行剪枝的算法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Basis vector analyses of back-propagation neural networks

Develops a polynomial basis function approach for modeling BP (backpropagation) neural networks. This method leads directly to a constructive proof of the BP approximation theorem. In addition, the basis vector approach provides a means to synthesize the BP neural network output as a polynomial function. An algorithm for pruning the useless basis vectors is also demonstrated.<>

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

[1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems

自引率

0.00%

发文量