BIMSA > BIMSA/Qiuzhen Colloquium Series on the Mathematics of AI Mean-field theory of learning dynamics in deep neural networks
Mean-field theory of learning dynamics in deep neural networks
组织者
沙伊莱什·拉尔 , 邬荣领
演讲者
Cengiz Pehlevan
时间
2024年03月25日 09:00 至 11:00
地点
Online
线上
Zoom 787 662 9899 (BIMSA)
摘要
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
演讲者介绍
Cengiz (pronounced "Jen·ghiz") 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.