Title: Phenomenon-Driven Deep Learning Research and Its Application in Combustion Problems
Speaker:
Zhi-Qin Xu
Associate Professor
Institute of Natural Sciences/School of Mathematical Sciences, Shanghai Jiao Tong University
Time: May 16th (Thursday) 10:00
Location: B-518,Lee Shau Kee Building of Science and Technology
host: Prof. Bin Yang
Abstract:
This report focuses on the fundamental research of phenomenon-driven deep learning. It will cover common phenomena such as the frequency principle and condensation phenomena, and aim to understand why neural networks exhibit good generalization ability under over-parameterization. On the application side, we will discuss the acceleration of combustion simulations using neural network algorithms.
Bio:
Zhi-Qin Xu is an associate professor at the Institute of Natural Sciences/School of Mathematical Sciences, Shanghai Jiao Tong University. Dr. Xu graduated from Zhiyuan College of Shanghai Jiao Tong University in 2012. In 2016, he graduated from Shanghai Jiao Tong University with a doctor's degree in applied mathematics. From 2016 to 2019, he was a postdoctoral fellow at NYU Abu Dhabi and the Courant Institute. He is the managing editor of Journal of Machine Learning.
供稿人：许志钦
审核人：刘有晟、游小清
