•  学术报告

关于举行哥伦比亚大学John Paisley教授学术报告会的通知

发布时间:2019-06-27文章来源:华南理工大学数学学院浏览次数:351

报告题目:Mixed Membership Recurrent Neural Networks

报  告  人:Prof. John Paisley(哥伦比亚大学)

报告时间:201972日下午16:00-17:00

报告地点:4号楼4318

邀  请  人:曾德炉  教授

欢迎广大师生前往!

数学学院

2019627

报告简介:

Models of sequential data such as the recurrent neural network (RNN) often implicitly treat a sequence as having a fixed time interval between observations and do not account for group-level effects when multiple sequences are observed. We propose a model for grouped sequential data based on the RNN that accounts for varying time intervals between observations in a sequence by learning a group-level parameter to which each sequence reverts as more time passes between observations. Our approach is motivated by the mixed membership framework, and can be used for dynamic topic modeling-type problems in which the distribution on topics (not the topics themselves) are evolving in time. We demonstrate our approach on two datasets: The Instacart set of 3.4 million online grocery orders made by 206K customers, and a UK retail set consisting of over 500K orders.

 

报告人简介:

John Paisley is an Associate Professor in the Department of Electrical Engineering at Columbia University, where he is also a member of the Data Science Institute. He received his Ph.D. in Electrical and Computer Engineering from Duke University, after which he was a post-doc in the Computer Science departments at Princeton University and University of California, Berkeley. John’s research is on machine learning. His interests include Bayesian modeling and inference techniques, Bayesian nonparametric methods, and applications in text and image processing.