alt text 

Zhi-Qin John Xu, 许志钦

Tenure-track Associate Professor, 副教授

Institute of Natural Sciences, 自然科学研究院

School of Mathematical Sciences, 数学科学学院

Shanghai Jiao Tong University, 上海交通大学

I work on deep learning and computational neuroscience. I obtained my B.S. in Physics (Zhiyuan College) and a Ph.D. degree in Mathematics from SJTU under the supervision of Profs. David Cai and Douglas Zhou. Before joining SJTU, I worked as a Postdoc at NYUAD and Courant Institute from 2016 to 2019.

materials

机器学习联合研讨计划机器学习与科学应用大会主页: c2sml.cn

A suggested notation for machine learning (通用机器学习符号) published by BAAI (北京智源), see page in github or the page in BAAI

slides at CSIAM 2020

B站课程

github code

Contact

alt text 

更多信息请关注我的公众号

Email: xuzhiqin at sjtu dot edu dot cn, Tel: 021-54742760

Office: 326, No.5 Science Building,No. 800 Dongchuan Road,

Shanghai Jiao Tong University,Minhang District, Shanghai

Research Interest

I am interested in understanding deep learning from training process, loss landscape, generalization and application. For example, we found a Frequency Principle (F-Principle) that deep neural networks (DNNs) often capture target functions from low frequency to high frequency in order during the training; we found an embedding principle that the loss landscape of a DNN “contains” all the critical points of all the narrower DNNs.

I am also interested in computational neuroscience, ranging from theoretical study and simulation to data analysis.