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

Discovering New Knowledge by Combining Symbolic Logic and Deep Learning

Research Project

Project/Area Number 22K21302
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund
Review Section 1002:Human informatics, applied informatics and related fields
Research InstitutionTokyo Institute of Technology

Principal Investigator

Phua Yin Jun  東京工業大学, 情報理工学院, 助教 (20963747)

Project Period (FY) 2022-08-31 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2023: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords深層学習 / ニューロシンボリック / 記号推論 / 知識発見 / ニューラルシンボリック / 深層機械学習
Outline of Research at the Start

本研究では新たな知識を発見できる人工知能(AI)を目指している.近年,タンパク質の構造を予測できるAIが発表されたが,その本質となる構造に関わる科学のメカニズムは解明されていない.これはそのAIに使われた技術がブラックボックスであることから起因している.この研究では,AIが直接「答え」を学習するのではなく,その「答え」に導くルールや説明を学習させる.それにより,AIが学習できたことを直接人間でも理解し取り込むことができる.

Outline of Final Research Achievements

This study focused on methods for discovering new human-readable knowledge by utilizing deep learning methods. First, we proposed a method that utilizes ensemble, where multiple models are trained, to stabilize the results for extracting features that are considered important by the models. Next, by utilizing a method to generate training data, which has been proposed for symbolic knowledge extraction methods, is applied to using generative AI in the incremental learning field. With this, we show that methods proposed for symbolic knowledge extraction can also be generalized to deep learning methods. Furthermore, we also proposed graph neural network models that are robust to noise that are inherent in graphs.

Academic Significance and Societal Importance of the Research Achievements

学術的意義として,実験データから重要な要素を抽出する基盤技術に貢献することができた.また,記号推論でよく使われる手法として,学習データを生成する手法は深層機械学習にも応用が可能であることを示した.さらに,生成AIの学術的応用を示すこともできた.社会的には,ノイズに対して頑健な手法を提案することで,実世界のデータをそのまま応用することが可能となる技術の開発に貢献した.本研究で開発した手法をさらに展開させることにより,実験データから新たな知識を抽出することができるAI技術へつながることが考えられる.

Report

(3 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • Research Products

    (4 results)

All 2024 2023 Other

All Int'l Joint Research (1 results) Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (2 results) (of which Int'l Joint Research: 2 results)

  • [Int'l Joint Research] Berlin Institute of Health (BIH)/Charite - Berlin University of Medicine/University of Heidelberg(ドイツ)

    • Related Report
      2022 Research-status Report
  • [Journal Article] resVAE ensemble: Unsupervised identification of gene sets in multi-modal single-cell sequencing data using deep ensembles2023

    • Author(s)
      Ten Foo Wei、Yuan Dongsheng、Jabareen Nabil、Phua Yin Jun、Eils Roland、Lukassen Soren、Conrad Christian
    • Journal Title

      Frontiers in Cell and Developmental Biology

      Volume: 11

    • DOI

      10.3389/fcell.2023.1091047

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] DEGNN: Dual Experts Graph Neural Network Handling both Edge and Node Feature Noise2024

    • Author(s)
      Tai Hasegawa
    • Organizer
      Pacific-Asia Conference on Knowledge Discovery and Data Mining 2024
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Class-Incremental Learning using Diffusion Model for Distillation and Replay2023

    • Author(s)
      Quentin Jodelet
    • Organizer
      1st Workshop on Visual Continual Learning, ICCV2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2022-09-01   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi