{"title":"Hopfield网络的泛化","authors":"J. Fontanari","doi":"10.1051/JPHYS:0199000510210242100","DOIUrl":null,"url":null,"abstract":"The performance of a Hopfield network in learning an extensive number of concepts having access only to a finite supply of typical data which exemplify the concepts is studied. The minimal number of examples which must be taught to the network in order it starts to create representations for the concepts is calculated analitically. It is shown that the mixture states play a crucial role in the creation of these representations","PeriodicalId":14747,"journal":{"name":"Journal De Physique","volume":"13 1","pages":"2421-2430"},"PeriodicalIF":0.0000,"publicationDate":"1990-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"36","resultStr":"{\"title\":\"Generalization in a Hopfield network\",\"authors\":\"J. Fontanari\",\"doi\":\"10.1051/JPHYS:0199000510210242100\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The performance of a Hopfield network in learning an extensive number of concepts having access only to a finite supply of typical data which exemplify the concepts is studied. The minimal number of examples which must be taught to the network in order it starts to create representations for the concepts is calculated analitically. It is shown that the mixture states play a crucial role in the creation of these representations\",\"PeriodicalId\":14747,\"journal\":{\"name\":\"Journal De Physique\",\"volume\":\"13 1\",\"pages\":\"2421-2430\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1990-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"36\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal De Physique\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1051/JPHYS:0199000510210242100\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal De Physique","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1051/JPHYS:0199000510210242100","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The performance of a Hopfield network in learning an extensive number of concepts having access only to a finite supply of typical data which exemplify the concepts is studied. The minimal number of examples which must be taught to the network in order it starts to create representations for the concepts is calculated analitically. It is shown that the mixture states play a crucial role in the creation of these representations
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
