学术报告|
当前位置:首页 > 科研 > 学术报告
发表时间:2018-10-25 阅读次数:213次
报告题目: 杰出校友讲坛第五期:Mathematics: Foundation of Machine Learning and AI
报 告 人:范剑青 教授
报告人所在单位:Princeton University
报告日期:2018-10-25 星期四
报告时间:16:00
报告地点:光华东辅楼102袁天凡报告厅
  
报告摘要:

This talk first gives an overview on how mathematical and computational methods have evolved with growing  dimensionality and sample sizes and become the foundation of modern machine learning and AI. It will also outline how ideas of trading modeling biases and variances have been developed into high-dimensional statistics and machine learning, with focus on deep learning models.  We will outline the challenges of mathematical sciences at this crossroad and offer some prospects. We will offer a general robustification principle and show how to use factor adjustments to deal with dependent measurements.  In particular, Factor Adjusted Robust Multiple testing (FarmTest) and Model selection (FarmSelect) will be introduced for high-dimensional statistical inference and model selection. The effectiveness of these methods will be revealed with an application to predicting bond risk premia using macroeconomic time series.  Further insights on the prospects of machine learning and AI will be offered.

海报

  
本年度学院报告总序号:235

Copyright © |2012 复旦大学数学科学学院版权所有 沪ICP备042465  

电话:+86(21)65642341 传真:+86(21)65646073