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

KUMAGAI WATARU  熊谷 亘

ORCIDConnect your ORCID iD *help
… Alternative Names

Kumagai Wataru  熊谷 亘

Less
Researcher Number 20747167
Other IDs
Affiliation (Current) 2025: オムロンサイニックエックス株式会社, リサーチアドミニストレイティブディビジョン, リサーチエンジニア
Affiliation (based on the past Project Information) *help 2024: オムロンサイニックエックス株式会社, リサーチアドミニストレイティブディビジョン, リサーチエンジニア
2020 – 2023: 東京大学, 大学院工学系研究科(工学部), 特任助教
2017 – 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, 研究員
Review Section/Research Field
Principal Investigator
Statistical science
Except Principal Investigator
Transformative Research Areas, Section (IV) / Basic Section 60030:Statistical science-related
Keywords
Principal Investigator
特徴抽出 / 汎化誤差 / 機械学習 / 畳み込み / ニューラル過程 / 群対称性 / 普遍近似定理 / パラメータ転移 / メタ学習 / 転移学習 … More
Except Principal Investigator
… More マルチモーダル学習 / 自由エネルギー原理 / 深層生成モデル / 情報転送 / 転移学習 / 多ドメインデータ / 最適輸送 / 最適化 / 機械学修 / 数理統計 / 数理統計学 / 機械学習 / データサイエンス / AI Less
  • Research Projects

    (3 results)
  • Research Products

    (15 results)
  • Co-Researchers

    (6 People)
  •  A Study on Deep Generative Models based on The Free Energy Principle

    • Principal Investigator
      鈴木 雅大
    • Project Period (FY)
      2023 – 2027
    • Research Category
      Grant-in-Aid for Transformative Research Areas (A)
    • Review Section
      Transformative Research Areas, Section (IV)
    • Research Institution
      The University of Tokyo
  •  Statistical Learning with feature extraction and information integration of High-dimensional, large-scale, multi-domain data

    • Principal Investigator
      Kanamori Takafumi
    • Project Period (FY)
      2019 – 2023
    • Research Category
      Grant-in-Aid for Scientific Research (B)
    • Review Section
      Basic Section 60030:Statistical science-related
    • Research Institution
      Tokyo Institute of Technology
  •  Theoretical Analysis of Transfer Learning and Its ApplicationsPrincipal Investigator

    • Principal Investigator
      Kumagai Wataru
    • Project Period (FY)
      2017 – 2022
    • Research Category
      Grant-in-Aid for Young Scientists (B)
    • Research Field
      Statistical science
    • Research Institution
      The University of Tokyo
      Institute of Physical and Chemical Research

All 2023 2021 2019 2018 2017

All Journal Article Presentation

  • [Journal Article] Uncertainty propagation for dropout-based Bayesian neural networks2021

    • Author(s)
      Mae Yuki、Kumagai Wataru、Kanamori Takafumi
    • Journal Title

      Neural Networks

      Volume: 144 Pages: 394-406

    • DOI

      10.1016/j.neunet.2021.09.005

    • Peer Reviewed / Open Access
    • Data Source
      KAKENHI-PROJECT-19H04071
  • [Journal Article] Spectral Embedded Deep Clustering2019

    • Author(s)
      Wada Yuichiro、Miyamoto Shugo、Nakagama Takumi、Andeol Leo、Kumagai Wataru、Kanamori Takafumi
    • Journal Title

      Entropy

      Volume: 21 Issue: 8 Pages: 795-795

    • DOI

      10.3390/e21080795

    • Peer Reviewed / Open Access / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-17K12653, KAKENHI-PROJECT-19H04071, KAKENHI-PROJECT-16K00044
  • [Journal Article] Variable Selection for Nonparametric Learning with Power Series Kernels2019

    • Author(s)
      Matsui Kota、Kumagai Wataru、Kanamori Kenta、Nishikimi Mitsuaki、Kanamori Takafumi
    • Journal Title

      Neural Computation

      Volume: 31 Issue: 8 Pages: 1718-1750

    • DOI

      10.1162/neco_a_01212

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-17K12653, KAKENHI-PROJECT-15H01678, KAKENHI-PROJECT-19H04071, KAKENHI-PROJECT-16K00044
  • [Journal Article] Risk bound of transfer learning using parametric feature mapping and its application to sparse coding2019

    • Author(s)
      Kumagai Wataru、Kanamori Takafumi
    • Journal Title

      Machine Learning

      Volume: 108 Issue: 11 Pages: 1975-2008

    • DOI

      10.1007/s10994-019-05805-2

    • Peer Reviewed
    • Data Source
      KAKENHI-PROJECT-17K12653, KAKENHI-PROJECT-15H01678, KAKENHI-PROJECT-19H04071, KAKENHI-PROJECT-16K00044
  • [Journal Article] Robust Label Prediction via Label Propagation and Geodesic <i>k</i>-Nearest Neighbor in Online Semi-Supervised Learning2019

    • Author(s)
      WADA Yuichiro、SU Siqiang、KUMAGAI Wataru、KANAMORI Takafumi
    • Journal Title

      IEICE Trans. Inf. & Syst.

      Volume: E102.D Issue: 8 Pages: 1537-1545

    • DOI

      10.1587/transinf.2018EDP7424

    • NAID

      130007686445

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2019-08-01
    • Language
      English
    • Peer Reviewed / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-17K12653, KAKENHI-PROJECT-19H04071
  • [Presentation] 局所探索型獲得関数に基づく能動的レベル集合推定法の提案2023

    • Author(s)
      國分裕太; 松井孝太; 沓掛健太郎; 熊谷亘; 金森敬文
    • Organizer
      情報論的学習理論ワークショップIBIS
    • Data Source
      KAKENHI-PROJECT-19H04071
  • [Presentation] Local Acquisition Function for Active Level Set Estimation2023

    • Author(s)
      Y. Kokubun, K. Matsui, K. Kutsukake, W. Kumagai, T. Kanamori
    • Organizer
      NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World
    • Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-19H04071
  • [Presentation] 転移学習から継続学習へ2019

    • Author(s)
      熊谷亘
    • Organizer
      科学研究費 基盤研究(A)「機械学習システムの社会実装に向けた次世代最適化技法の研究」による2019年度ワークショップ
    • Invited
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] 転移学習から継続学習へ2019

    • Author(s)
      熊谷亘
    • Organizer
      情報系 WINTER FESTA Episode 5
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] Foundations of transfer learning and its application to multi-center prognostic prediction.2019

    • Author(s)
      K. Matsui, W. Kumagai, K. Kanamori, M. Nisikimi, S. Matsui, T. Kanamori
    • Organizer
      2019 WNAR/IMS/JR Annual Meeting
    • Invited / Int'l Joint Research
    • Data Source
      KAKENHI-PROJECT-19H04071
  • [Presentation] 転移学習の数理2018

    • Author(s)
      熊谷亘
    • Organizer
      第二回理研AIP数理系合同合宿
    • Invited
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] Wasserstein距離を用いた転移学習の理論解析2018

    • Author(s)
      熊谷亘
    • Organizer
      第21回情報論的学習理論ワークショップ
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] パラメータ転移学習における汎化誤差の評価2017

    • Author(s)
      熊谷亘
    • Organizer
      科研費シンポジウム「統計学, 機械学習の数理とその応用」
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] パラメータ転移学習におけるリスク上界2017

    • Author(s)
      熊谷亘
    • Organizer
      統計学・機械学習若手シンポジウム「大規模複雑データに対する統計・機械学習のアプローチ」
    • Data Source
      KAKENHI-PROJECT-17K12653
  • [Presentation] パラメータ転移学習におけるリスク上界2017

    • Author(s)
      熊谷亘
    • Organizer
      2017年度 統計関連学会連合大会
    • Data Source
      KAKENHI-PROJECT-17K12653
  • 1.  Kanamori Takafumi (60334546)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 4 results
  • 2.  竹之内 高志 (50403340)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 3.  松井 孝太 (50737111)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 3 results
  • 4.  川島 孝行 (60846210)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 5.  武田 朗子 (80361799)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 results
  • 6.  鈴木 雅大 (30823885)
    # of Collaborated Projects: 1 results
    # of Collaborated Products: 0 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