首 页机构概况机构设置科研人才队伍合作交流研究生教育博士后图书馆创新文化党群园地院重点实验室彭桓武中心信息公开
  学术活动
  您现在的位置:首页 > 学术活动 > Lunch Seminar
Training Boltzmann machines for unsupervised learning using extended mean field approximations
2016-10-25  【 】【打印】【关闭

Institute of Theoretical Physics

Chinese Academy of Sciences

 Key Laboratory of Theoretical Physics

Seminar

Title

题目

Training Boltzmann machines for unsupervised learning using extended mean field approximations

Speaker

报告人

Marylou Gabrie

Affiliation

所在单位

École Normale Supérieure

Date

日期

10月25日10:30-11:30

Venue

地点

Room 6420, ITP new building

 

Abstract

摘要

Boltzmann machines are undirected neural networks useful for unsupervised machine learning. In particular, a simple bipartite version - called Restricted Boltzmann machines (RBMs) - has been widely popularized by the discovery of fast training algorithms, relying on approximate Monte Carlo Markov Chains. Realizing that training RBMs is closely related to the inverse Ising problem, a notoriously hard statistical physics problem, we designed an alternative deterministic procedure based on the Thouless-Anderson-Palmer approach. Our algorithm, improving on the naive mean-field approximation, provides performance equal to the commonly used MCMC algorithms while also providing a clear and easy to evaluate objective function to follow progress along training. Moreover, this strategy can be generalized in many ways, including for new network architectures (e.g. deep Boltzmann machines) or for new types of data (e.g. continuous variables with a known prior distribution).

Contact Person

所内联系人

Pan Zhang
IE6.0浏览器,1024X768分辨率 版权所有 © 中国科学院理论物理研究所
地址:北京市海淀区中关村东路55号 邮政编码:100190
京ICP备05002865号】 京公网安备1101080094号