Yasaman Bahri, Jonathan Kadmon, Jeffrey Pennington, S. Schoenholz, Jascha Narain Sohl-Dickstein, S. Ganguli
{"title":"Statistical Mechanics of Deep Learning","authors":"Yasaman Bahri, Jonathan Kadmon, Jeffrey Pennington, S. Schoenholz, Jascha Narain Sohl-Dickstein, S. Ganguli","doi":"10.1146/annurev-conmatphys-031119-050745","DOIUrl":null,"url":null,"abstract":"The recent striking success of deep neural networks in machine learning raises profound questions about the theoretical principles underlying their success. For example, what can such deep networks...","PeriodicalId":7925,"journal":{"name":"Annual Review of Condensed Matter Physics","volume":"11 1","pages":"501-528"},"PeriodicalIF":14.3000,"publicationDate":"2020-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1146/annurev-conmatphys-031119-050745","citationCount":"171","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annual Review of Condensed Matter Physics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1146/annurev-conmatphys-031119-050745","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, CONDENSED MATTER","Score":null,"Total":0}
引用次数: 171
Abstract
The recent striking success of deep neural networks in machine learning raises profound questions about the theoretical principles underlying their success. For example, what can such deep networks...
期刊介绍：
Since its inception in 2010, the Annual Review of Condensed Matter Physics has been chronicling significant advancements in the field and its related subjects. By highlighting recent developments and offering critical evaluations, the journal actively contributes to the ongoing discourse in condensed matter physics. The latest volume of the journal has transitioned from gated access to open access, facilitated by Annual Reviews' Subscribe to Open initiative. Under this program, all articles are now published under a CC BY license, ensuring broader accessibility and dissemination of knowledge.
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
