Statistical Mechanics of Deep Learning

IF 14.3 1区物理与天体物理 Q1 PHYSICS, CONDENSED MATTER

Annual Review of Condensed Matter Physics Pub Date : 2020-03-16 DOI:10.1146/annurev-conmatphys-031119-050745

Yasaman Bahri, Jonathan Kadmon, Jeffrey Pennington, S. Schoenholz, Jascha Narain Sohl-Dickstein, S. Ganguli

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...

查看原文本刊更多论文

深度学习统计力学

最近，深度神经网络在机器学习领域取得了惊人的成功，这引发了人们对其成功背后的理论原理的深刻质疑。例如，这样的深度网络……

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Annual Review of Condensed Matter Physics PHYSICS, CONDENSED MATTER-

CiteScore

47.40

自引率

0.90%

发文量

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.