{"title":"使用放松找到一个木偶","authors":"Geoffrey E. Hinton","doi":"10.5555/3015508.3015523","DOIUrl":null,"url":null,"abstract":"The problem of finding a puppet in a configuration of overlapping, transparent rectangles is used to show how a relaxation algorithm can extract the globally best figure from a network of conflicting local interpretations.","PeriodicalId":133823,"journal":{"name":"Artificial Intelligence and the Simulation of Behaviour","volume":"119 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1976-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":"{\"title\":\"Using Relaxation to find a Puppet\",\"authors\":\"Geoffrey E. Hinton\",\"doi\":\"10.5555/3015508.3015523\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The problem of finding a puppet in a configuration of overlapping, transparent rectangles is used to show how a relaxation algorithm can extract the globally best figure from a network of conflicting local interpretations.\",\"PeriodicalId\":133823,\"journal\":{\"name\":\"Artificial Intelligence and the Simulation of Behaviour\",\"volume\":\"119 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1976-07-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"24\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence and the Simulation of Behaviour\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5555/3015508.3015523\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence and the Simulation of Behaviour","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5555/3015508.3015523","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The problem of finding a puppet in a configuration of overlapping, transparent rectangles is used to show how a relaxation algorithm can extract the globally best figure from a network of conflicting local interpretations.