{"title":"神经网络的非参数估计","authors":"G. Lugosi, K. Zeger","doi":"10.1109/ISIT.1994.394876","DOIUrl":null,"url":null,"abstract":"We show that properly trained neural networks provide universally consistent nonparametric estimators. The results apply to regression estimation, conditional median estimation, curve fitting, pattern recognition and learning concepts. The estimators minimize the empirical L/sub p/-error.<<ETX>>","PeriodicalId":331390,"journal":{"name":"Proceedings of 1994 IEEE International Symposium on Information Theory","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Nonparametric estimation using neural networks\",\"authors\":\"G. Lugosi, K. Zeger\",\"doi\":\"10.1109/ISIT.1994.394876\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We show that properly trained neural networks provide universally consistent nonparametric estimators. The results apply to regression estimation, conditional median estimation, curve fitting, pattern recognition and learning concepts. The estimators minimize the empirical L/sub p/-error.<<ETX>>\",\"PeriodicalId\":331390,\"journal\":{\"name\":\"Proceedings of 1994 IEEE International Symposium on Information Theory\",\"volume\":\"13 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1994-06-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of 1994 IEEE International Symposium on Information Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIT.1994.394876\",\"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 of 1994 IEEE International Symposium on Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.1994.394876","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We show that properly trained neural networks provide universally consistent nonparametric estimators. The results apply to regression estimation, conditional median estimation, curve fitting, pattern recognition and learning concepts. The estimators minimize the empirical L/sub p/-error.<>
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
