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

Cortex inspired Deep Learning Algorithms and Applications on Knowledge Processing

Research Project

Project/Area Number 15H05327
Research Category

Grant-in-Aid for Young Scientists (A)

Allocation TypeSingle-year Grants
Research Field Web informatics, Service informatics
Research InstitutionThe University of Tokyo

Principal Investigator

Nakayama Kotaro  東京大学, 大学院工学系研究科(工学部), 特任講師 (00512097)

Project Period (FY) 2015-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥14,560,000 (Direct Cost: ¥11,200,000、Indirect Cost: ¥3,360,000)
Fiscal Year 2018: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2017: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2016: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2015: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
KeywordsDeep Learning / 人工知能 / 計算科学 / 機械学習 / 脳科学 / Webデータ / スパースデータ / データサイエンス / AI / データ解析 / 人口知能 / ニュートラルネットワーク / スケーラビリティ / GPGPU
Outline of Final Research Achievements

In this research project, we aimed to develop scalable deep learning algorithms using the latest brain science findings, and have conducted research on flexible knowledge processing mechanism. There are two points to achieve this mechanism; a general-purpose knowledge processing model applicable to various tasks (applications) and a calculation model optimized for parallel processing capable of processing large-scale data in real time is there. The basic & theoretical research part and applied research part have been progressed as scheduled, and the results have been published as international conference papers and domestic journals.

Academic Significance and Societal Importance of the Research Achievements

第三次AIブームを牽引しているDeep Learning技術は、計算時間や計算コストが大きな課題であった。本研究課題では,最新の脳科学の知見を活かしてより効率的かつ柔軟な知識処理機構を持つDeep Learning手法を実現することを目指して研究を進めてきた。予定どおり基礎研究と応用研究についての研究を進めることができ、国際会議・国内論文誌含め、多くの論文として対外発表することができた。

Report

(5 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Annual Research Report
  • 2016 Annual Research Report
  • 2015 Annual Research Report
  • Research Products

    (19 results)

All 2018 2017 2016 2015

All Journal Article (4 results) (of which Peer Reviewed: 3 results) Presentation (15 results) (of which Int'l Joint Research: 7 results,  Invited: 3 results)

  • [Journal Article] Wikipediaの編集履歴から学習したベクトル表現によるコンテンツの人気予測2018

    • Author(s)
      野中尚輝, 中山浩太郎, 松尾豊
    • Journal Title

      電子情報通信学会論文誌

      Volume: 4 Pages: 657-668

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Wikipediaの編集履歴から学習したベクトル表現によるコンテンツの人気予測2018

    • Author(s)
      野中尚輝, 中山浩太郎, 松尾豊
    • Journal Title

      電子情報通信学会論文誌(特集号)

      Volume: 4 Pages: 657-668

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] GeSdA - GPU上でのAutoencoder処理並列化による高速Deep Learningの実装2016

    • Author(s)
      中山浩太郎・松尾豊
    • Journal Title

      情報処理学会論文紙

      Volume: 70 Pages: 1-9

    • NAID

      170000148037

    • Related Report
      2016 Annual Research Report
  • [Journal Article] GeSdA - GPU上でのAutoencoder処理並列化による高 速Deep Learningの実装2016

    • Author(s)
      中山浩太郎、松尾豊
    • Journal Title

      情報処理学会論文誌(TOD)

      Volume: 70号 Pages: 1-9

    • NAID

      170000148037

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Presentation] An analysis of human gaze data for autonomous medical image diagnostics2018

    • Author(s)
      A. R. A. Ghani, K. Nishanth, Ai Nakajima, N. Kimura, P. Radkohl, S. Iwai, Y. Kawazoe, Y. Iwasawa, K. Nakayama, Y. Matsuo
    • Organizer
      The 28th Annual Conference of the Japanese Neural Network Society (JNNS), Workshop
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Expert-based reward function training: the novel method to train sequence generators2018

    • Author(s)
      Joji Toyama, Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo
    • Organizer
      International Conference of Learning Representation (ICLR18) Workshop
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Designing Efficient Neural Attention Systems Towards Achieving Human-level Sharp Vision2018

    • Author(s)
      A.R. A.Ghani, N. Koganti, A. Solano, Y. Iwasawa, K. Nakayama, Y. Matsuo
    • Organizer
      International Conference of Learning Representation (ICLR18) Workshop
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Censoring Representations with Multiple-Adversaries over Random Subspaces2018

    • Author(s)
      Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo
    • Organizer
      International Conference of Learning Representation (ICLR18) Workshop
    • Related Report
      2018 Annual Research Report
  • [Presentation] Virtual Reality as a User-friendly Interface for Learning from Demonstrations.2018

    • Author(s)
      Nishanth Koganti, Abdul R. A. Ghani, Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo
    • Organizer
      Conference on Human Factors in Computing Systems, (CHI) Demo track
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] マルチエージェントによるDeep Learningの提案2017

    • Author(s)
      黒滝 紘生,中山 浩太郎,松尾 豊
    • Organizer
      人工知能学会全国大会
    • Place of Presentation
      愛知県名古屋市(ウィンクあいち)
    • Year and Date
      2017-06-23
    • Related Report
      2016 Annual Research Report
  • [Presentation] 画像とテキストの潜在的な意味情報を用いたニューラル翻訳モデルの提案2017

    • Author(s)
      冨山 翔司,味曽野 雅史,鈴木 雅大,中山 浩太郎,松尾 豊
    • Organizer
      人工知能学会全国大会
    • Place of Presentation
      愛知県名古屋市(ウィンクあいち)
    • Year and Date
      2017-06-23
    • Related Report
      2016 Annual Research Report
  • [Presentation] Contents Popularity Prediction by Vector Representation Learned from User Action History2017

    • Author(s)
      Naoki Nonaka, Kotaro Nakayama, Yutaka Matsuo
    • Organizer
      DATA ANALYTICS
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Privacy Issues Regarding the Application of DNNs to Activity-Recognition using Wearables and Its Countermeasures by Use of Adversarial Training2017

    • Author(s)
      Yusuke Iwasawa, Kotaro Nakayama, Ikuko Yairi and Yutaka Matsuo
    • Organizer
      International Joint Conference on Artificial Intelligence (IJCAI2017)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Joint Multimodal Learning with Deep Generative Models2017

    • Author(s)
      Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
    • Organizer
      ICLR 2017 workshop
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Deep Learningの基礎と応用2017

    • Author(s)
      中山浩太郎
    • Organizer
      第33回ネットワークシステム・情報ネットワーク研究ワークショップ
    • Place of Presentation
      残波ロイヤルホテル
    • Related Report
      2016 Annual Research Report
    • Invited
  • [Presentation] Deep Learning技術の仕組み2016

    • Author(s)
      中山浩太郎
    • Organizer
      人工知能学会セミナー
    • Place of Presentation
      慶應義塾大学 日吉キャンパス
    • Year and Date
      2016-06-30
    • Related Report
      2015 Annual Research Report
    • Invited
  • [Presentation] マルチエージェントによるDeep Learningの提案2016

    • Author(s)
      黒滝 紘生、中山浩太郎、松尾豊
    • Organizer
      人工知能学会全国大会
    • Place of Presentation
      北九州国際会議場
    • Year and Date
      2016-06-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] 逆畳み込みニューラルネットワークを用いた輪郭検出2016

    • Author(s)
      味曽野 雅史、中山浩太郎、松尾豊
    • Organizer
      人工知能学会全国大会
    • Place of Presentation
      北九州国際会議場
    • Year and Date
      2016-06-06
    • Related Report
      2015 Annual Research Report
  • [Presentation] Deep Learning のパッケージ: Pylearn2とTorch72015

    • Author(s)
      中山浩太郎
    • Organizer
      日本神経回路学会主催セミナー
    • Place of Presentation
      電気通信大学
    • Year and Date
      2015-09-06
    • Related Report
      2015 Annual Research Report
    • Invited

URL: 

Published: 2015-04-16   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi