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

Development of the MDL Principle and Its Applications

Research Project

Project/Area Number 18H03291
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionKyushu University

Principal Investigator

Takeuchi Junichi  九州大学, システム情報科学研究院, 教授 (80432871)

Co-Investigator(Kenkyū-buntansha) 三村 和史  広島市立大学, 情報科学研究科, 教授 (40353297)
村田 昇  早稲田大学, 理工学術院, 教授 (60242038)
長岡 浩司  電気通信大学, 大学院情報理工学研究科, 名誉教授 (80192235)
Project Period (FY) 2018-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2020: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2019: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2018: ¥9,100,000 (Direct Cost: ¥7,000,000、Indirect Cost: ¥2,100,000)
Keywords記述長最小原理 / MDL原理 / 深層学習 / 情報理論 / MRI / サイバーセキュリティ / 教師あり学習 / 汎化誤差 / スパース学習 / 磁気共鳴画像法 / 超解像 / 汚染ガウスモデル / 進化系統樹 / 圧縮センシング / 情報幾何学 / Markov連鎖 / メタ学習 / スパース重ね合わせ符号 / Markovモデル / 誤り訂正符号 / 局所指数族バンドル / 非負値行列因子分解 / 確率的コンプレキシティ / 機械学習
Outline of Final Research Achievements

We studied development of learning theory based on the Minimum Description Length (MDL) principle and its application. Concerning the MDL principle, after reconsidering our previous results on enhancement of Barron and Cover theory (BC theory) to supervised learning, we considered the relation to deep learning. We also studied the connection between the BC theory and the stochastic complexity and its application to non-exponential families, including the mixture families and the simple contaminated Gaussian location families. As for real application, we studied MRI image reconstruction based on deep learning and data analysis for caber security. For the former topic, we proposed a high speed reconstruction method which enjoyed good image quality for MR Angiography. For the latter topic, we developed a clustering method based on the MDL principle and phylogenetic trees and showed that its performance was good by experiment using real IoT malware data.

Academic Significance and Societal Importance of the Research Achievements

様々な分野で高い実用性を示している深層学習の理論を確立することを目的に,機械学習の基盤的理論の一つであるMDL原理からのアプローチを試みている.本課題の遂行中に,MDL原理を教師あり学習に用いるための重要な条件が明らかになった.現在この観点に基づいた深層学習の解析を進めており,その結果有用な知見が得られると予想される.

Report

(4 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Annual Research Report
  • 2018 Annual Research Report
  • Research Products

    (23 results)

All 2021 2020 2019 2018 Other

All Int'l Joint Research (1 results) Journal Article (8 results) (of which Peer Reviewed: 8 results,  Open Access: 6 results) Presentation (13 results) (of which Int'l Joint Research: 8 results) Patent(Industrial Property Rights) (1 results)

  • [Int'l Joint Research] Yale University(米国)

    • Related Report
      2019 Annual Research Report
  • [Journal Article] An Extended Scheme for Shape Matching with Local Descriptors2021

    • Author(s)
      IWATA Kazunori、YAMAMOTO Hiroki、MIMURA Kazushi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D Issue: 2 Pages: 285-293

    • DOI

      10.1587/transinf.2020EDP7134

    • NAID

      130007979519

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2021-02-01
    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Integrated analysis of cell shape and movement in moving frame2021

    • Author(s)
      Heryanto Yusri Dwi、Cheng Chin-Yi、Uchida Yutaka、Mimura Kazushi、Ishii Masaru、Yamada Ryo
    • Journal Title

      Biology Open

      Volume: 10 Issue: 3

    • DOI

      10.1242/bio.058512

    • NAID

      120007006754

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Real-Time Detection of Global Cyberthreat Based on Darknet by Estimating Anomalous Synchronization Using Graphical Lasso2020

    • Author(s)
      HAN Chansu、SHIMAMURA Jumpei、TAKAHASHI Takeshi、INOUE Daisuke、TAKEUCHI Jun'ichi、NAKAO Koji
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E103.D Issue: 10 Pages: 2113-2124

    • DOI

      10.1587/transinf.2020EDP7076

    • NAID

      130007920585

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2020-10-01
    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Minimum Description Length Principle in Supervised Learning With Application to Lasso2020

    • Author(s)
      Kawakita Masanori、Takeuchi Jun'ichi
    • Journal Title

      IEEE Transactions on Information Theory

      Volume: 66 Issue: 7 Pages: 4245-4269

    • DOI

      10.1109/tit.2020.2998577

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Single-Molecule Localization by Voxel-Wise Regression Using Convolutional Neural Network.2020

    • Author(s)
      Aritake T, Hino H, Namiki S, Asanuma D, Hirose K, Murata N
    • Journal Title

      Results in Optics

      Volume: 1 Pages: 100019-100019

    • DOI

      10.1016/j.rio.2020.100019

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] An improved analysis of least squares superposition codes with bernoulli dictionary2019

    • Author(s)
      Takeishi Yoshinari、Takeuchi Jun’ichi
    • Journal Title

      Japanese Journal of Statistics and Data Science

      Volume: 2 Issue: 2 Pages: 591-613

    • DOI

      10.1007/s42081-019-00057-9

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Learning Scale and Shift-Invariant Dictionary for Sparse Representation2019

    • Author(s)
      Aritake Toshimitsu、Murata Noboru
    • Journal Title

      Machine Learning, Optimization, and Data Science

      Volume: 11943 Pages: 472-483

    • DOI

      10.1007/978-3-030-37599-7_39

    • ISBN
      9783030375980, 9783030375997
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A unified global convergence analysis of multiplicative update rules for nonnegative matrix factorization2018

    • Author(s)
      N. Takahashi, J. Katayama, M. Seki, and J. Takeuchi
    • Journal Title

      Computational Optimization and Applications

      Volume: 71 Issue: 1 Pages: 221-250

    • DOI

      10.1007/s10589-018-9997-y

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed
  • [Presentation] On MDL Estimation for Simple Contaminated Gaussian Location Families2020

    • Author(s)
      K. Miyamoto, J. Takeuchi
    • Organizer
      the 2020 International Symposium on Information Theory and Its Applications
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Investigating Behavioral Differences between IoT Malware via Function Call Sequence Graphs2020

    • Author(s)
      R. Kawasoe, C. Han, R. Isawa, T. Takahashi, J. Takeuchi
    • Organizer
      the 36th ACM/SIGAPP Symposium On Applied Computing
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Property of Quantum Decoding for Sourlas Codes of Which Tuples Are Randomly Decimated2020

    • Author(s)
      Sangook Lee, Kazunori Iwata, Kazushi Mimura
    • Organizer
      the 2020 International Symposium on Information Theory and Its Applications
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Improved MDL Estimators Using Local Exponential Family Bundles Applied to Mixture Families2019

    • Author(s)
      K. Miyamoto, A. R. Barron, J. Takeuchi
    • Organizer
      019 IEEE International Symposium on Information Theory
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Real-Time Detection of Malware Activities by Analyzing Darknet Traffic Using Graphical Lasso2019

    • Author(s)
      C. Han, J. Shimamura, T. Takahashi, D. Inoue, M. Kawakita, J. Takeuchi, K. Nakao
    • Organizer
      The 18th IEEE International Conference on Trust, Security and Privacy in Computing and Communications
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Dynamics of Damped Approximate Message Passing Algorithms2019

    • Author(s)
      K. Mimura, J. Takeuchi
    • Organizer
      2019 IEEE Information Theory Workshop
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Magnetic Resonance Angiography Image Restoration by Super Resolution Based on Deep Learning2019

    • Author(s)
      S. Kitazaki, M. Kawakita, Y. Jitsumatsu, S. Kuhara, A. Hiwatashi, J. Takeuchi
    • Organizer
      2019 World Congress of European Society for Magnetic Resonance in Medicine and Biology
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Fast Algorithm for Constructing Phylogenetic Trees with Application to IoT Malware Clustering2019

    • Author(s)
      T. He, C. Han, R. Isawa, T. Takahashi, S. Kijima, J. Takeuchi, K. Nakao,
    • Organizer
      the 24th International Conference on Neural Information Processing
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 深層学習超解像を用いた磁気共鳴血管画像の復元2019

    • Author(s)
      北崎自然,川喜田雅則,實松豊,久原重英,樋渡昭雄,竹内純一
    • Organizer
      電子情報通信学会技術研究報告 IBISML2018-114
    • Related Report
      2018 Annual Research Report
  • [Presentation] ダンピングOAMPの経路積分法による解析2018

    • Author(s)
      三村和史,竹内純一
    • Organizer
      第41回情報理論とその応用シンポジウム
    • Related Report
      2018 Annual Research Report
  • [Presentation] 非負値行列因子分解とMDL規準によるマーケットプレイスにおける商品推薦手法2018

    • Author(s)
      荒野洋輔,三宅悠介,川喜田雅則,竹内純一
    • Organizer
      第21回情報論的学習理論ワークショップ
    • Related Report
      2018 Annual Research Report
  • [Presentation] 深層学習超解像を用いたMRI再構成の検討2018

    • Author(s)
      北崎自然,川喜田雅則,實松豊,久原重英,竹内純一
    • Organizer
      電子情報通信学会技術研究報告 IBISML2018-16
    • Related Report
      2018 Annual Research Report
  • [Presentation] 非負値行列因子分解とMDL規準によるマーケットプレイスのためのデータ解析2018

    • Author(s)
      荒野洋輔, 三宅悠介, 川喜田雅則, 竹内純一
    • Organizer
      電子情報通信学会技術研究報告 IBISML2018-8
    • Related Report
      2018 Annual Research Report
  • [Patent(Industrial Property Rights)] 磁気共鳴画像高速再構成法2020

    • Inventor(s)
      竹内、實松、川喜田、北崎、久原
    • Industrial Property Rights Holder
      竹内、實松、川喜田、北崎、久原
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2020-025707
    • Filing Date
      2020
    • Related Report
      2019 Annual Research Report

URL: 

Published: 2018-04-23   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi