• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Takeishi Naoya  武石 直也

ORCIDConnect your ORCID iD *help
Researcher Number 20824030
Other IDs
Affiliation (Current) 2026: 東京大学, 先端科学技術研究センター, 講師
2026: 東京大学, 大学院工学系研究科(工学部), 講師
Affiliation (based on the past Project Information) *help 2026: 東京大学, 大学院工学系研究科(工学部), 講師
2023 – 2026: 東京大学, 先端科学技術研究センター, 講師
2018 – 2020: 国立研究開発法人理化学研究所, 革新知能統合研究センター, 特別研究員
Review Section/Research Field
Principal Investigator
Transformative Research Areas, Section (IV) / Basic Section 61030:Intelligent informatics-related / Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related / Basic Section 60030:Statistical science-related / 1002:Human informatics, applied informatics and related fields
Except Principal Investigator
Basic Section 25010:Social systems engineering-related / Transformative Research Areas, Section (IV)
Keywords
Principal Investigator
機械学習 / データ駆動型推論 / 専門家知識 / 事前知識 / 統計的機械学習 / 流体計測 / 偏微分方程式 / 統計的関係学習 / 異常検知 / ナレッジグラフ / センサデータ解析 / 知識ベース / シミュレータ … More
Except Principal Investigator
… More 動的システム / 機械学習 / 運用最適化 / 動的システム学習 / 異常検知・診断 / 半教師ありドメイン適応 / 残存寿命予測 / 潜在健全指標 / 健全性予測・監視 / 生物集団 / 動物行動 / 数理モデル / 移動系列 / インタラクション / 集団運動 Less
  • Research Projects

    (10 results)
  • Research Products

    (31 results)
  • Co-Researchers

    (10 People)
  •  自由にクエリできないシミュレーションに基づく推論Principal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2026 – 2029
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 61030:Intelligent informatics-related
      Basic Section 60030:Statistical science-related
      Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related
    • Research Institution
      The University of Tokyo
  •  Theoretical and methodological foundation for data-driven inference with application to high-dimensional measurementArea Organizer

    • Area Organizer
      武石 直也
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (B)
  •  Data-Driven Inference: Mathematical Foundation and Application to High-Dimensional MeasurementsPrincipal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (B)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      The University of Tokyo
  •  Development of Data-Driven Inference Methods Based on Structures of Dynamical SystemsPrincipal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (B)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      The University of Tokyo
  •  データ駆動型推論の数理・計算基盤構築と高次元計測への展開Principal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (B)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      The University of Tokyo
  •  力学系の構造を活用した革新的データ駆動型推論手法の開発Principal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2025 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (B)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      The University of Tokyo
  •  Study on Prognostics and Operation Optimization based on Latent Health Index Models

    • Principal Investigator
      矢入 健久
    • Project Period (FY)
      2024 – 2027
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 25010:Social systems engineering-related
    • Research Institution
      The University of Tokyo
  •  Development of advanced machine learning methods in cooperation with prior knowledge as simulatorsPrincipal Investigator

    • Principal Investigator
      武石 直也
    • Project Period (FY)
      2022 – 2025
    • Research Category
      Grant-in-Aid for Early-Career Scientists
    • Review Section
      Basic Section 61030:Intelligent informatics-related
    • Research Institution
      The University of Tokyo
      Institute of Physical and Chemical Research
  •  Technologies for rule/learning-based analysis and intervention policy in hierarchical bio-navigation

    • Principal Investigator
      藤井 慶輔
    • Project Period (FY)
      2021 – 2025
    • Research Category
      Grant-in-Aid for Transformative Research Areas (A)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      Nagoya University
  •  Intelligent Sensor Data Analysis based on Cooperation of Knowledge Bases and Statistical Machine LearningPrincipal Investigator

    • Principal Investigator
      Takeishi Naoya
    • Project Period (FY)
      2018 – 2020
    • Research Category
      Grant-in-Aid for Research Activity Start-up
    • Review Section
      1002:Human informatics, applied informatics and related fields
    • Research Institution
      Institute of Physical and Chemical Research

All 2024 2023 2022 2021 2020 2019 2018

All Journal Article Presentation

  • [Journal Article] Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling2024

    • Author(s)
      Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda
    • Journal Title

      Neural Networks

      Volume: 171 Pages: 42-50

    • DOI

      10.1016/j.neunet.2023.11.068

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-21H05300, KAKENHI-PLANNED-22H05106, KAKENHI-PROJECT-22H00516, KAKENHI-PROJECT-21H04892, KAKENHI-PROJECT-23K27972
  • [Journal Article] Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations2024

    • Author(s)
      Keisuke Fujii, Kazushi Tsutsui, Atom Scott, Hiroshi Nakahara, Naoya Takeishi, Yoshinobu Kawahara
    • Journal Title

      Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART'24)

      Volume: 2 Pages: 27-39

    • DOI

      10.5220/0012261100003636

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-22K17673, KAKENHI-PLANNED-21H05300, KAKENHI-PROJECT-21H04892, KAKENHI-PROJECT-23K27972
  • [Journal Article] Mimicking Better by Matching the Approximate Action Distribution2024

    • Author(s)
      Joao A. Candido Ramos, Lionel Blonde, Naoya Takeishi, Alexandros Kalousis
    • Journal Title

      Proceedings of the 41st International Conference on Machine Learning

      Volume: - Pages: 5513-5532

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Journal Article] Estimating counterfactual treatment outcomes over time in complex multiagent scenarios2024

    • Author(s)
      Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda
    • Journal Title

      IEEE Transactions on Neural Networks and Learning Systems

      Volume: - Issue: 2 Pages: 1-15

    • DOI

      10.1109/tnnls.2024.3361166

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-21H05300, KAKENHI-PROJECT-22H00516, KAKENHI-PROJECT-21H04892, KAKENHI-PROJECT-23K27972
  • [Journal Article] Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability2023

    • Author(s)
      Maciej Falkiewicz, Naoya Takeishi, Imahn Shekhzadeh, Antoine Wehenkel, Arnaud Delaunoy, Gilles Louppe, Alexandros Kalousis
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 36 Pages: 1082-1099

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Journal Article] Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections2022

    • Author(s)
      Naoya Takeishi, Keisuke Fujii, Koh Takeuchi, Yoshinobu Kawahara
    • Journal Title

      SIAM Journal on Applied Dynamical Systems

      Volume: 21(2) Issue: 2 Pages: 1030-1058

    • DOI

      10.1137/21m1399907

    • Peer Reviewed
    • Data Source
      KAKENHI-ORGANIZER-21H05293, KAKENHI-PLANNED-21H05300
  • [Journal Article] Estimating counterfactual treatment outcomes over time in complex multi-vehicle simulation2022

    • Author(s)
      Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi, Naoya Takeishi, Yoshinobu Kawahara, Kazuya Takeda
    • Journal Title

      30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2022)

      Volume: 7 Pages: 1-4

    • Peer Reviewed
    • Data Source
      KAKENHI-PLANNED-21H05300
  • [Journal Article] Learning Dynamics Models with Stable Invariant Sets2021

    • Author(s)
      Naoya Takeishi and Kawahara Yoshinobu
    • Journal Title

      Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence

      Volume: -

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Journal Article] Learning interaction rules from multi-animal trajectories via augmented behavioral models2021

    • Author(s)
      Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryoya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu, Yoshinobu Kawahara
    • Journal Title

      Advances in Neural Information Processing Systems (NeurIPS'21)

      Volume: 34

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PLANNED-21H05300
  • [Journal Article] Knowledge-Based Regularization in Generative Modeling2020

    • Author(s)
      Naoya Takeishi、Yoshinobu Kawahara
    • Journal Title

      Proceedings of the 29th International Joint Conference on Artificial Intelligence

      Volume: -

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Journal Article] Neural Gray-Box Identification of Nonlinear Partial Differential Equations2019

    • Author(s)
      Sasaki Riku、Takeishi Naoya、Yairi Takehisa、Hori Koichi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 11671 Pages: 309-321

    • DOI

      10.1007/978-3-030-29911-8_24

    • ISBN
      9783030299101, 9783030299118
    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Journal Article] Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection2019

    • Author(s)
      Naoya Takeishi
    • Journal Title

      Proceedings of the 2019 International Conference on Data Mining Workshops

      Volume: - Pages: 793-798

    • DOI

      10.1109/icdmw.2019.00117

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Journal Article] Kernel Learning for Data-Driven Spectral Analysis of Koopman Operators2019

    • Author(s)
      Naoya Takeishi
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 101 Pages: 956-971

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Journal Article] Factorially Switching Dynamic Mode Decomposition for Koopman Analysis of Time-Variant Systems2018

    • Author(s)
      N. Takeishi, T. Yairi and Y. Kawahara
    • Journal Title

      Proceedings of 2018 IEEE Conference on Decision and Control (CDC'18)

      Volume: -- Pages: 6402-6408

    • DOI

      10.1109/cdc.2018.8619846

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-18H03287, KAKENHI-PROJECT-19K21550
  • [Presentation] Toward Bayesian Deep Grey-box Modeling2024

    • Author(s)
      Naoya Takeishi
    • Organizer
      International Conference on Scientific Computing and Machine Learning
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] 確率微分方程式の学習において物理モデルおよび正則化を導入する効果の検証2024

    • Author(s)
      大坂 光, 武石 直也, 矢入 健久
    • Organizer
      第27回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] Learning Neural Observables for Koopman Operators2024

    • Author(s)
      Naoya Takeishi
    • Organizer
      Workshop on Koopman Operators in Robotics, RSS 2024
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] 機械学習と科学モデル2024

    • Author(s)
      武石 直也
    • Organizer
      第38回人工知能学会全国大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] 機械学習と数理モデル:順問題と逆問題のデータ駆動型解法2024

    • Author(s)
      武石 直也
    • Organizer
      日本地震学会2024年度秋季大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] Toward Bayesian Deep Grey-box Modeling2024

    • Author(s)
      Naoya Takeishi
    • Organizer
      International Conference on Scientific Computing and Machine Learning
    • Int'l Joint Research
    • Data Source
      KAKENHI-PLANNED-21H05300
  • [Presentation] 深層学習による時系列異常検知手法の課題点2024

    • Author(s)
      中島 琢登, 矢入 健久, 武石 直也
    • Organizer
      第1回 スマートマニュファクチャリングとシステム健全性管理研究会
    • Data Source
      KAKENHI-PROJECT-24K01110
  • [Presentation] 深層ハイブリッドモデルとその研究開発への適用にむけて2024

    • Author(s)
      武石 直也
    • Organizer
      第27回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] データと物理モデルを融合した確率的モデリングとその時空間データへの適用2024

    • Author(s)
      大坂 光, リュー ジュンフイ, 武石 直也, 矢入 健久
    • Organizer
      第38回人工知能学会全国大会
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] 機械学習と科学モデルの融合2023

    • Author(s)
      武石直也
    • Organizer
      第46回日本神経科学大会
    • Invited
    • Data Source
      KAKENHI-PLANNED-21H05300
  • [Presentation] 機械学習と科学モデルの融合2023

    • Author(s)
      武石 直也
    • Organizer
      第46回日本神経科学大会
    • Invited
    • Data Source
      KAKENHI-PROJECT-20K19869
  • [Presentation] 生物集団の軌跡から相互作用の規則を学習するための拡張行動モデル2021

    • Author(s)
      藤井慶輔, 武石直也, 筒井和詩, 藤岡慧明, 西海望, 田中良弥, 福代三華, 井出薫, 河野裕美, 依田憲, 高橋晋, 飛龍志津子, 河原吉伸
    • Organizer
      第24回 情報論的学習理論ワークショップ (IBIS 2021)
    • Data Source
      KAKENHI-PLANNED-21H05300
  • [Presentation] 安定不変集合をもつ力学系の学習2020

    • Author(s)
      武石 直也, 河原 吉伸
    • Organizer
      第23回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Presentation] 再構成誤差のシャープレイ値による異常検知の説明2019

    • Author(s)
      武石 直也
    • Organizer
      第22回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Presentation] 時変動的モード分解2019

    • Author(s)
      武石 直也
    • Organizer
      第33回人工知能学会全国大会
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Presentation] 知識グラフによる生成モデル学習の正則化2018

    • Author(s)
      武石 直也
    • Organizer
      第21回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-19K21550
  • [Presentation] Knowledge-Based Distant Regularization in Learning Probabilistic Models2018

    • Author(s)
      Naoya Takeishi、Kosuke Akimoto
    • Organizer
      The 8th International Workshop on Statistical Relational AI
    • Data Source
      KAKENHI-PROJECT-19K21550
  • 1.  池田 正弘 (00749690)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 2.  赤嶺 政仁 (00835465)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 3.  藤井 慶輔 (70747401)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 6 results
  • 4.  田部井 靖生 (20589824)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 5.  村上 久 (20755467)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 6.  西海 望 (10760390)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 2 results
  • 7.  矢入 健久 (90313189)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 1 results
  • 8.  カーン サミル (10898836)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 9.  KAWAHARA Yoshinobu
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results
  • 10.  筒井 和詩
    # of Collaborated Projects: 0 results
    # of Collaborated Products: 1 results

URL: 

Are you sure that you want to link your ORCID iD to your KAKEN Researcher profile?
* This action can be performed only by the researcher himself/herself who is listed on the KAKEN Researcher’s page. Are you sure that this KAKEN Researcher’s page is your page?

この研究者とORCID iDの連携を行いますか?
※ この処理は、研究者本人だけが実行できます。

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi