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

2020 Fiscal Year Final Research Report

Developing a brain-integrated AI system with personality

Research Project

  • PDF
Project/Area Number 18K18141
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61060:Kansei informatics-related
Research InstitutionNational Institute of Information and Communications Technology

Principal Investigator

Nishida Satoshi  国立研究開発法人情報通信研究機構, 脳情報通信融合研究センター脳情報通信融合研究室, 主任研究員 (90751933)

Project Period (FY) 2018-04-01 – 2021-03-31
Keywords人工知能 / 脳情報 / 個性 / 深層学習 / 畳み込みニューラルネット / 感性 / fMRI / 脳解読
Outline of Final Research Achievements

Toward the realization of the AI system that shows human-like behavior and personality, this study developed a technique that integrates personal brain information modeled from brain activity into a convolutional neural network (CNN). In the validation of the technique using real data, the technique more highly improves the estimation performance of CNNs in various pattern recognition tasks when brain information was more important for the estimation in the tasks. In addition, the estimation of the brain-integrated CNNs reflected the individual variability of human perception. These results suggest that the brain-integration technique we developed has the potential to make AI behavior more human-like and give personality to AI.

Free Research Field

認知神経科学

Academic Significance and Societal Importance of the Research Achievements

本研究で開発した技術は、特定の認識課題に特化した従来の脳情報融合技術と異なり、多様な認識問題へ適用可能な汎用的技術である点に独自性がある。また脳情報の個性を反映したAIシステムを構築した点も世界初であり、開発技術の学術的価値は極めて高い。人間とAIが調和する未来の情報社会を実現するために、人間らしい振る舞いを行う個性を有したAIの誕生が望まれる。本研究成果はそのようなAIを実現するための基盤技術として、情報社会の発展に大きな貢献をもたらす。

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi