选择最佳神经网络

[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society Pub Date : 1990-11-27 DOI:10.1109/IECON.1990.149309

D. B. Fogel

{"title":"选择最佳神经网络","authors":"D. B. Fogel","doi":"10.1109/IECON.1990.149309","DOIUrl":null,"url":null,"abstract":"A relationship between optimal network design and statistical model identification is described. A derivative of Akaike's information criterion (AIC) is given. This modification yields an information statistic which can be used to select a best network for binary classification problems objectively. The technique can be extended to problems with an arbitrary number of classes.<<ETX>>","PeriodicalId":253424,"journal":{"name":"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society","volume":"249 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Selecting an optimal neural network\",\"authors\":\"D. B. Fogel\",\"doi\":\"10.1109/IECON.1990.149309\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A relationship between optimal network design and statistical model identification is described. A derivative of Akaike's information criterion (AIC) is given. This modification yields an information statistic which can be used to select a best network for binary classification problems objectively. The technique can be extended to problems with an arbitrary number of classes.<<ETX>>\",\"PeriodicalId\":253424,\"journal\":{\"name\":\"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society\",\"volume\":\"249 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1990-11-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IECON.1990.149309\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IECON.1990.149309","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 5

摘要

描述了最佳网络设计与统计模型识别之间的关系。给出了 Akaike 信息准则 (AIC) 的导数。这种修正产生了一种信息统计量，可用于客观地为二元分类问题选择最佳网络。该技术还可扩展到具有任意数量类别的问题。

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

Selecting an optimal neural network

A relationship between optimal network design and statistical model identification is described. A derivative of Akaike's information criterion (AIC) is given. This modification yields an information statistic which can be used to select a best network for binary classification problems objectively. The technique can be extended to problems with an arbitrary number of classes.<>

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

[Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society

CiteScore

1.40

自引率

0.00%

发文量