多隐层前馈神经网络自适应回归估计的收敛速率

Proceedings. International Symposium on Information Theory, 2005. ISIT 2005. Pub Date : 2005-10-31 DOI:10.1109/ISIT.2005.1523580

M. Kohler, A. Krzyżak

{"title":"多隐层前馈神经网络自适应回归估计的收敛速率","authors":"M. Kohler, A. Krzyżak","doi":"10.1109/ISIT.2005.1523580","DOIUrl":null,"url":null,"abstract":"We present a general bound on the expected L2 error of adaptive least squares estimates. By applying it to multiple hidden layer feedforward neural network regression function estimates we are able to obtain optimal (up to log factor) rates of convergence for Lipschitz classes and fast rates of convergence for some classes of regression functions such as additive functions","PeriodicalId":166130,"journal":{"name":"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rates of convergence for adaptive regression estimates with multiple hidden layer feedforward neural networks\",\"authors\":\"M. Kohler, A. Krzyżak\",\"doi\":\"10.1109/ISIT.2005.1523580\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a general bound on the expected L2 error of adaptive least squares estimates. By applying it to multiple hidden layer feedforward neural network regression function estimates we are able to obtain optimal (up to log factor) rates of convergence for Lipschitz classes and fast rates of convergence for some classes of regression functions such as additive functions\",\"PeriodicalId\":166130,\"journal\":{\"name\":\"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.\",\"volume\":\"56 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2005-10-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIT.2005.1523580\",\"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. International Symposium on Information Theory, 2005. ISIT 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.2005.1523580","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

给出了自适应最小二乘估计的期望L2误差的一般界。通过将其应用于多个隐层前馈神经网络回归函数估计，我们能够获得Lipschitz类的最优(高达对数因子)收敛速率和某些类回归函数(如加性函数)的快速收敛速率

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

Rates of convergence for adaptive regression estimates with multiple hidden layer feedforward neural networks

We present a general bound on the expected L2 error of adaptive least squares estimates. By applying it to multiple hidden layer feedforward neural network regression function estimates we are able to obtain optimal (up to log factor) rates of convergence for Lipschitz classes and fast rates of convergence for some classes of regression functions such as additive functions

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. International Symposium on Information Theory, 2005. ISIT 2005.

自引率

0.00%

发文量