山东大学新闻网
山大邮箱 | 投稿系统 | 高级检索 | 旧版回顾
复杂检索

视点首页 > 学术预告 > 正文

数学学院珠峰讲坛第266期:Uncertainty Quantification in Deep Learning through Stochastic Maximum Principle

发布日期:2020年12月01日 18:57 点击次数:

时间 12月5日(星期六)9:30-10:30 地点 腾讯会议(ID:315 433 872)
本站讯 讲座时间 2020-12-05 09:30:00

一、题目

Uncertainty Quantification in Deep Learning through Stochastic Maximum Principle

二、主讲人

Yanzhao Cao

三、摘要

We develop a probabilistic machine learning method, which formulates a class of stochastic neural networks by a stochastic optimal control problem. An efficient stochastic gradient descent algorithm is introduced under the stochastic maximum principle framework. Convergence analysis for stochastic gradient descent optimization and numerical experiments for applications of stochastic neural networks are carried out to validate our methodology in both theory and performance.

四、主讲人简介

Professor Yanzhao Cao is currently the Don Logan Endowed Chair in Mathematics at Auburn University. He received both his BA and Master degrees in mathematics from Jilin University (1983, 1986), and PhD in mathematics from Virginia Tech (1996). He is an associate editor of SIAM Journal in Numerical Analysis and Journal of Integral Equations and Applications, and a managing editor of Communications in Mathematical Research. He is also serving as the President of SIAM Southeast and Atlantic Section. His expertise is in numerical methods for partial differential equations and stochastic computing.

五、邀请人

赵卫东 数学学院教授

六、时间

12月5日(周六)9:30-10:30

七、地点

腾讯会议,会议ID:315 433 872

https://meeting.tencent.com/s/lfPkUiwcO1BY

八、主办方

山东大学数学学院


【作者:桑军帅    来自:数学学院    编辑:新闻网工作室    责任编辑:甘传昀 蒋晓涵  】

 匿名发布 验证码 看不清楚,换张图片
0条评论    共1页   当前第1拖动光标可翻页查看更多评论

最新发布

新闻排行

免责声明

您是本站的第: 位访客

您是本站的第:64104994 位访客

新闻中心电话:0531-88362831 0531-88369009 联系信箱:xwzx@sdu.edu.cn

建议使用IE8.0以上浏览器和1366*768分辨率浏览本站以取得最佳浏览效果

欢迎关注山大视点微信