{"title":"The mathematical theory of learning algorithms for Boltzmann machines","authors":"H. Sussmann","doi":"10.1109/IJCNN.1989.118278","DOIUrl":null,"url":null,"abstract":"The author analyzes a version of a well-known learning algorithm for Boltzmann machines, based on the usual alternation between learning and hallucinating phases. He outlines the rigorous proof that, for suitable choices of the parameters, the evolution of the weights follows very closely, with very high probability, an integral trajectory of the gradient of the likelihood function whose global maxima are exactly the desired weight patterns.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International 1989 Joint Conference on Neural Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IJCNN.1989.118278","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The author analyzes a version of a well-known learning algorithm for Boltzmann machines, based on the usual alternation between learning and hallucinating phases. He outlines the rigorous proof that, for suitable choices of the parameters, the evolution of the weights follows very closely, with very high probability, an integral trajectory of the gradient of the likelihood function whose global maxima are exactly the desired weight patterns.<>
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
