Research

Academic exchange

学术报告二十四:An Optimization View Point of Deep Learning: From Theory to Applications (四)

数学与统计学院学术报告[2020] 024

(高水平大学建设系列报告376)


 

报告题目: An Optimization View Point of Deep Learning: From Theory to Applications ()

报告人: 冯象初 教授西安电子科技大学

报告时间:20206121440-1630

报告地点: 腾讯会议240 454 397    

报告内容:

Deep learning has become a milestone in a lot of applications ranging from computer vision, to natural langue processing, to auto drive. In this talk, I will give a general analysis of deep learning from the optimization point of view. To be more specific, I will show that how does each of the three ingredients in deep learning — training data, network architecture and optimization algorithms — affect the overall learning and generalization. Meanwhile, I will expose some tricks that really help improving the training efficiency.

报告人简历:

冯象初,西安电子科技大学数学与统计学院教授,博士生导师,陕西省计算数学协会副理事长,陕西省工业与应用数学学会会员。主要从事数值分析、小波理论及应用、图像处理中的数学问题等方面的研究和教学工作。多次在香港浸会大学、香港理工大学作访问学者。获陕西省优秀回国留学人员奖1项,陕西省教委科技进步一等奖1项,教育部科技进步三等奖1项。主持和参加国家自然科学基金、陕西省自然科学基金、博士点基金等多项科研项目。发表学术论文70余篇,出版《数值泛函与小波理论》、《图像处理的变分和偏微分方程方法》等专著。

欢迎感兴趣的师生参加!

 

 

                      数学与统计学院

 

                      2020612

 

Friendly Link:

Address:中国广东深圳大学科技楼四层    Postcode:518060    TEL:0755-26534791

Copyright © 2006-2014 MATH.SZU.EDU.CN All Rights Reserved