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

Integrating symbolic-based AI and pattern-based AI using psychological findings

Research Project

Project/Area Number 19K22884
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionNational Institute of Informatics

Principal Investigator

Ichise Ryutaro  国立情報学研究所, 情報学プリンシプル研究系, 准教授 (00332156)

Project Period (FY) 2019-06-28 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2020: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2019: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Keywords人工知能 / 機械学習 / 記号処理 / パターン処理
Outline of Research at the Start

人工知能には,記号処理とパターン処理の2つの対立する代表的なアプローチがある.従来の人工知能では,2つのアプローチを問題領域に応じて選択し,それぞれ別個に応用されてきた.本研究では,これまでに別個で使われていた記号的人工知能とパターン的人工知能の判断を有機的に統合する手法を解明することを目的とする.そのために,本研究では,心理学の理論に基づき,この2つを統合することを目指す.

Outline of Final Research Achievements

There are two representative approaches to Artificial Intelligence: symbolic-based approach and pattern-based approach. The purpose of this research is to elucidate a method to integrate symbolic-based AI and pattern-based AI. For this purpose, we investigated the characteristics of the two approaches and developed a technique to integrate them.

Academic Significance and Societal Importance of the Research Achievements

人工知能の世界においては,人工知能が使う原理に関して,長年,パターンか記号かの論争が続いている.本研究では,それぞれの長所を統合する挑戦的な課題を設定した.学術的には,人工知能のアプローチを根本から見直す意義がある.また,社会的には,2つのアプローチを統合することで,意思決定の透明化がなされ,安心して人工知能技術の導入を進められるようになる意義がある.

Report

(3 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • Research Products

    (4 results)

All 2021 2020 2019

All Journal Article (4 results) (of which Peer Reviewed: 4 results,  Open Access: 3 results)

  • [Journal Article] Explanatory Rule Generation for Advanced Driver Assistant Systems2021

    • Author(s)
      Juha Hovi, Ryutaro Ichise
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D

    • NAID

      130008082104

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Towards Interpretable Reinforcement Learning with State Abstraction Driven by External Knowledge2020

    • Author(s)
      Nicolas Bougie, Ryutaro Ichise
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E103.D Pages: 2143-2153

    • NAID

      130007920639

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Skill-based Curiosity for Intrinsically Motivated Reinforcement Learning2020

    • Author(s)
      Nicolas Bougie, Ryutaro Ichise
    • Journal Title

      Machine Learning

      Volume: 109 Pages: 493-512

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Feasibility Study: Rule Generation for Ontology-based Decision-making Systems2019

    • Author(s)
      Juha Hovi, Ryutaro Ichise
    • Journal Title

      Proceedings of the 9th Joint International Semantic Technology Conference

      Volume: CCIS 1157 Pages: 88-99

    • Related Report
      2019 Research-status Report
    • Peer Reviewed

URL: 

Published: 2019-07-04   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi