清华主页 EN
导航菜单

Mean-field theory of learning dynamics in deep neural networks

来源: 03-25

时间:09:00-11:00, 2024-03-25

地点:ZOOM: 787 662 9899 PW: BIMSA

组织者: Rongling Wu Shailesh Lal

主讲人:Cengiz Pehlevan (SEAS, Harvard University)

Abstract

Learning dynamics of deep neural networks is complex. While previous approaches made advances in mathematical analyses of the dynamics of two-layer neural networks, addressing deeper networks have been challenging. In this talk, I will present a mean field theory of the learning dynamics of deep networks in the feature-learning regime and discuss its implications for practice.

References:

https://arxiv.org/abs/2205.09653

https://arxiv.org/abs/2305.18411

https://arxiv.org/abs/2309.16620


Speaker Intro

Cengiz (pronounced "Jenghiz") comes to Harvard SEAS from the Flatiron Institute's Center for Computational Biology (CCB), where he was a a research scientist in the neuroscience group. Before CCB, Cengiz was a postdoctoral associate at Janelia Research Campus, and before that a Swartz Fellow at Harvard. Cengiz received a doctorate in physics from Brown University and undergraduate degrees in physics and electrical engineering from Bogazici University. He is a native of Tosya, Turkey.

返回顶部
相关文章
  • Mean-field theory of learning dynamics in deep neural networks

    AbstractLearning dynamics of deep neural networks is complex. While previous approaches made advances in mathematical analysis of the dynamics of two-layer neural networks, addressing deeper networks have been challenging. In this talk, I will present a mean field theory of the learning dynamics of deep networks and discuss its practical implications

  • Conductivity Imaging using Deep Neural Networks

    Speaker Dr. Bangti Jin received his PhD degree in applied mathematics from the Chinese University of Hong Kong, Hong Kong, in 2008. Currently he is a professor of mathematics at Department of Mathematics, The Chinese University of Hong Kong. Previously he was a lecturer, reader and professor of inverse problems at Department of Computer Science, University College London (2014-2022), an assista...