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

Percolative Learning and its applications

Research Project

Project/Area Number 18H03305
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61040:Soft computing-related
Research InstitutionYokohama National University

Principal Investigator

Nagao Tomoharu  横浜国立大学, 大学院環境情報研究院, 教授 (10180457)

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: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥8,190,000 (Direct Cost: ¥6,300,000、Indirect Cost: ¥1,890,000)
Keywords機械学習 / 深層学習 / ニューラルネットワーク / 進化計算法 / マルチモーダル / 時系列予測 / マルチモーダル学習
Outline of Final Research Achievements

We previously developed "PLM: Percolative Learning Method" which is a kind of learning method for layered deep neural networks. In this project, we studied theory, methods and applications of PLM. In PLM, we can "percolate" Aux data which are used only for learning into Main data which are used for learning and testing. We proved that PLM could achieve the precision rate higher than a conventional deep neural network experimentally. We dealt with time dependence data prediction and realization of software-sensor, and we showed that PLM is effective for various fields.

Academic Significance and Societal Importance of the Research Achievements

これまでの神経回路網や深層学習では,学習時のみ利用できるデータは,学習しても実際の運用の際に使えなくなるので,結局利用されてこなかった.これに対して,我々が開発した浸透学習を使うことで,そのようなデータを有効に活用することができるようになった.本事業において浸透学習の理論・方法・応用について具体的な検討を行い,浸透学習が有効であることを示すことができた.今後,様々な分野で浸透学習を利用することが考えられ,その効果と波及効果は大きいと考えられる.

Report

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

    (3 results)

All 2021 2019 2018

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (1 results) (of which Invited: 1 results) Patent(Industrial Property Rights) (1 results)

  • [Journal Article] Percolative Learning: Time-Series Prediction from Future Tendencies2018

    • Author(s)
      Kazuki Takaishi, Masayuki Kobayashi, Miku Yanagimoto and Tomoharu Nagao
    • Journal Title

      Conference: 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

      Volume: 1 Pages: 1643-1648

    • DOI

      10.1109/smc.2018.00285

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 深層学習から浸透学習へ2019

    • Author(s)
      長尾智晴
    • Organizer
      応用脳科学コンソーシアム 応用脳科学アカデミー
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Patent(Industrial Property Rights)] ニューラルネットワークシステム、学習制御装置、演算方法、学習制御方法およびプログラム2021

    • Inventor(s)
      長尾智晴,小林雅幸
    • Industrial Property Rights Holder
      横浜国立大学
    • Industrial Property Rights Type
      特許
    • Filing Date
      2021
    • Related Report
      2020 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