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

A Study on Deep Convolutional Neural Network Considering the Mechanism of Visual Information Processing in the Brain

Research Project

Project/Area Number 17K00251
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Perceptual information processing
Research InstitutionTokyo University of Technology

Principal Investigator

KIKUCHI Masayuki  東京工科大学, コンピュータサイエンス学部, 講師 (20291437)

Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords深層学習 / 畳み込みニューラルネットワーク / 脳 / 視覚系 / モデル / Deep Learning / 深層畳み込みニューラルネットワーク / 図地分離 / 進化的計算 / U-Net / AlexNet / Neocognitron / 畳込みニューラルネットワーク / 視覚情報処理 / パターン認識
Outline of Final Research Achievements

In order to refine the CNN (Deep Convolutional Neural Network) causing the innovation on our society, this research project aimed to add novel functions to the CNN and investigated the properties of the CNN from the viewpoint of brain information processing. First, the usefulness of the medial axis representation which is regarded to be encoded in the brain, is examined by applying medial axis transformation to input patterns. In addition, the model structure was generated automatically by an evolutionary computation to approach the function of the brain having rich structures. On the other hand, we investigated the possibility of U-Net approximating the visual system roughly, to simulate visual functions such as figure-ground separation and visual completions, and performed spine extraction from CT images. Moreover, we investigated the relationship between the accuracy of recognition by CNN and the response distribution, and gained a foothold for efficient model setting.

Academic Significance and Societal Importance of the Research Achievements

昨今,社会の諸領域に変革をもたらしつつある深層学習の中核技術であるCNNは元々,1960年代の一部の脳科学的知見を工学的にモデリングしたものがベースになっている.更なる脳の知見の投入により,深層学習はもっと進化する可能性も考えられる.万能のように扱われる既存の深層学習も現状では狭い問題設定の枠内でのみ有効性が確認されており,人間の脳ほどの汎用性はまだ獲得されていないこと,そして大量のデータがないと高い能力を発揮することができず,少量のデータのみでも内在する性質を適切に学び取れるヒトに及ばないことなどの難点があり,本研究課題の観点はこれらを解決する糸口を提供し得るものと言える.

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (10 results)

All 2020 2019 2018

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (9 results) (of which Int'l Joint Research: 3 results,  Invited: 2 results)

  • [Journal Article] Effectiveness of Pseudo 3D Feature Learning for Spinal Segmentation by CNN with U-Net Architecture2019

    • Author(s)
      Naofumi Shigeta, Mikoto Kamata, Masayuki Kikuchi
    • Journal Title

      Journal of Image and Graphics

      Volume: ー

    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] ロバストなパターン認識に対する中心軸表現の効果の検討2020

    • Author(s)
      菊池 眞之,島森和輝
    • Organizer
      第36回ファジィシステムシンポジウム
    • Related Report
      2019 Annual Research Report
  • [Presentation] 遺伝的プログラミングによる図地分離モデルの自動生成2019

    • Author(s)
      菅野路哉, 菊池眞之
    • Organizer
      日本神経回路学会第29回全国大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 凹凸特徴に基づく物体認知の性質とメカニズム2019

    • Author(s)
      菊池眞之
    • Organizer
      第23回日本知能情報ファジィ学会 しなやかな行動の脳工学研究部会 研究会・第121回 日本知能情報ファジィ学会 関西支部例会
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] Effectiveness of Pseudo 3D Feature Learning for Spinal Segmentation by CNN with U-Net Architecture2019

    • Author(s)
      Naofumi Shigeta, Mikoto Kamata, Masayuki Kikuchi
    • Organizer
      ICFIP2019(International Conference on Frontiers of Image Processing)
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] U-Netを利用したCT画像からの脊椎領域抽出タスクにおける立体形状学習の有用性2019

    • Author(s)
      重田尚郁,鎌田理詩,菊池眞之
    • Organizer
      電子情報通信学会ニューロコンピューティング研究会
    • Related Report
      2018 Research-status Report
  • [Presentation] ヒトの視覚特性と認知、情報処理のメカニズム2018

    • Author(s)
      菊池眞之
    • Organizer
      技術情報協会セミナー「ARにおける視覚情報の認知,処理のメカニズムと現実空間との整合性」
    • Related Report
      2018 Research-status Report
    • Invited
  • [Presentation] U-NetによるCT画像における脊椎の自動検出2018

    • Author(s)
      鎌田理詩, 菊池眞之, 庄野 逸, 林 勲, 福島邦彦
    • Organizer
      電子情報通信学会ニューロコンピューティング研究会技術報告
    • Related Report
      2017 Research-status Report
  • [Presentation] Identification and region extraction of symmetry by deep learning2018

    • Author(s)
      Yoshiki Goto, Masayuki Kikuchi
    • Organizer
      NCSP2018 (Nonlinear Circuits, Communications and Signal Processing)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Automatic detection of spine in CT image by U-Net2018

    • Author(s)
      Mikoto Kamata, Kunihiko Fukushima, Hayaru Shouno, Isao Hayashi, Masayuki Kikuchi
    • Organizer
      NCSP2018 (Nonlinear Circuits, Communications and Signal Processing)
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi