Imperfect Information Learning Team

Masashi Sugiyama (Ph.D.)

Title

Team Leader

History

2001	Assistant Professor, Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan.
2003	Associate Professor, Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan.
2014	Professor, Department of Complexity Science and Engineering, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan. (Present)
2016	Director, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan. (Present)

Members

Team Leader

Masashi Sugiyama

WEBSITE
Research Scientist

Gang Niu
Postdoctoral Researcher

Voot Tangkaratt
Postdoctoral Researcher

Miao Xu
Senior Visiting Scientist

Shinichi Nakajima
Visiting Scientist

Bo Han
Visiting Scientist

Junya Honda
Visiting Scientist

Ryohei Kasai
Visiting Scientist

Takayuki Osa
Visiting Scientist

Florian Yger
Visiting Scientist

Shuhei Yamamoto
Visiting Scientist

Hisashi Yoshida
Visiting Scientist

Masahiro Yukawa

Introduction

Recently, machine learning technology with big data has been actively investigated and its effectiveness has been demonstrated. However, depending on application domains, it is difficult or even it is not possible to collect a large amount of data. In the Imperfect Information Learning Team, for various machine learning tasks including supervised learning, unsupervised learning, and reinforcement learning, we develop novel algorithms that allow accurate learning from limited information. We also elucidate their theoretical properties and apply them to various real-world applications ranging from fundamental science to business.

Main Research Field

Computer Science

Research Field

Engineering / Mathematics

Research Subjects

Development of machine learning algorithms from imperfect information
Theoretical analysis of machine learning algorithms
Real-world application of machine learning algorithms

RIKEN Website URL

http://www.riken.jp/en/research/labs/aip/generic_tech/imperfect_inf_learn/