Updated on 2024/05/23

写真b

 
TAKI Masato
 
*Items subject to periodic update by Rikkyo University (The rest are reprinted from information registered on researchmap.)
Affiliation*
Graduate School of Artificial Intelligence and Science Master's Program in Artificial Intelligence and Science
College of Science Department of Physics
Graduate School of Artificial Intelligence and Science Doctoral Program in Artificial Intelligence and Science
Title*
Associate Professor
Research Theme*
  • 深層学習の基礎研究を通じて、その成功の背後にあるメカニズムを明らかにし、より良い手法へ改善することを目指している。例えば、より説明性の高い深層学習アーキテクチャをデザインすることでデータから科学的な知識を抽出したり、あるいは敵対的事例などの深層学習の未解明な部分の研究を行っている。また、深層学習を使って医療や神経科学などのサイエンスにおけるデータを分析したり、機械学習・深層学習を産業へ応用する社会実装なども行っている。【略歴】2004年東京大学理学部物理学科卒業。2009年東京大学大学院理学系研究科物理学専攻修了。2009年から2012年まで京都大学基礎物理学研究所博士研究員。その後、理化学研究所 基礎科学特別研究員、数理創造プログラム(iTHEMS)上級研究員を経て現職。

  • Campus Career*
    • 4 2022 - Present 
      Graduate School of Artificial Intelligence and Science   Master's Program in Artificial Intelligence and Science   Associate Professor
    • 4 2022 - Present 
      Graduate School of Artificial Intelligence and Science   Doctoral Program in Artificial Intelligence and Science   Associate Professor
    • 4 2021 - Present 
      College of Science   Department of Physics   Associate Professor
    • 4 2021 - 3 2022 
      Graduate School of Artificial Intelligence and Science   Artificial Intelligence and Science   Associate Professor
    • 4 2020 - 3 2021 
      Graduate School of Artificial Intelligence and Science   Artificial Intelligence and Science   Specially Appointed Associate Professor
     

    Research Projects

    • Mathematics and application of deep learning

      Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research 

      More details

      6 2022 - 3 2027

      Grant number:22H05116

      Grant amount:\101010000 ( Direct Cost: \77700000 、 Indirect Cost:\23310000 )

      researchmap

    • Research on performance of deep learning performance based on random matrix theory

      Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research 

      Taki Masato

      More details

      6 2017 - 3 2020

      Grant number:17K19989

      Grant amount:\6240000 ( Direct Cost: \4800000 、 Indirect Cost:\1440000 )

      The origin of the high performance of deep learning (generalization performance) is a big mystery. The goal of this project was to tackle it with a mathematical and applied approach. Various computer experiments related to deep learning were able to be carried out by the computer environment that was prepared by this grant project. As a result, we have accumulated practical know-how that contributes to the performance improvement of deep learning. Utilizing that know-how, we were able to conduct applied research on experimental science data, etc., while taking advantage of the strengths of machine learning. In that case, the practical side by the computer experiment was important, but the improvement and adjustment of the machine learning model by the mathematical analysis also played a big role.

      researchmap