Mean-field theory of learning dynamics in deep neural networks-求真书院

研讨班

首页 > 书院学术 > 至美数学 > 研讨班

Mean-field theory of learning dynamics in deep neural networks

来源： 10-10

时间：2023-10-10 Tue 10:00-12:00

地点：A3-1a-205 ZOOM: 537 192 5549（PW: BIMSA） Abstract

组织者：Seyed Hamidreza Mofidi, Shailesh Lal, Hossein Yavartanoo

主讲人：Cengiz Pehlevan SEAS, Harvard University

Abstract

Learning 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.

返回顶部

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...
View more
Learning constitutive models with neural networks
AbstractIn this talk, I will introduce some work of learning constitutive equations in fluid mechanics and geophysics based on machine learningSpeaker Intro熊繁升，现任北京雁栖湖应用数学研究院助理研究员，曾任北京应用物理与计算数学研究所所聘博士后。先后毕业于中国地质大学(北京)、清华大学，美国耶鲁大学联合培养博士。研究兴趣主要集中于基于机器学习算法(DNN、PINN、DeepONet等)求解微分方程模型正/反问题...
View more

书院学术

Mean-field theory of learning dynamics in deep neural networks

Conductivity Imaging using Deep Neural Networks

Learning constitutive models with neural networks

友情链接 HYPERLINK：