DATE Akira

写真a

Affiliation

Engineering educational research section Information and Communication Technology Program

Title

Associate Professor

Contact information

Contact information

Homepage

http://www.cs.miyazaki-u.ac.jp/~date/index-j.html

External Link

Degree 【 display / non-display

  • 博士(工学) ( 1996.9   東京農工大学 )

Research Interests 【 display / non-display

  • Information and communication

Research Areas 【 display / non-display

  • Life Science / Neuroscience-general

  • Informatics / Life, health and medical informatics

  • Informatics / Kansei informatics

Education 【 display / non-display

  • Tokyo University of Agriculture and Technology   Graduate School, Division of Engineering

    - 1996.9

      More details

    Country:Japan

  • The University of Electro-Communications   Faculty of Electro Communications

    - 1991.3

      More details

    Country:Japan

Professional Memberships 【 display / non-display

  • 人工知能学会

    2018.4 - 2021.3

  • プロジェクト TECUM

    2018.1

  • 情報処理学会

    2016.8 - 2021.3

  • 日本学術振興会

    2010.8 - 2011.7

  • 計測自動制御学会

    2009.4 - 2010.3

display all >>

 

Papers 【 display / non-display

  • A Self-Organization Model Developing Higher Order Units by Self-Test Learning

    Akira Date, Shunsuke Hanai

    IEICE Technical Report   118 ( 284 )   419 - 424   2018.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ニューラルネットが「分かる」とは: 暴力的ではないアプローチ

    伊達 章

    夏のプログラミング・シンポジウム2016「教育・学習」報告集   2017.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  • On the composition systems and their application to handwritten character recognition

    Akira Date, Hikari Kubota, Yusuke Yamada

    116 ( 259 )   19 - 24   2016.10

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    Most of the pattern recognition methods currently used in the real world application are statistical ones, such as feedforward neural networks, Markov random fields while syntactical or grammatical approaches are not exploited. Since current generation feedforaward neural networks are expected not to be able to learn the underlying structure of the outer world, we believe that grammatical approach is promising. S. Geman et al.(1998) developed mathematical foundations of composition systems. Compositionality is with re-usability and hierarchy, and we see it everywhere (e.g. vision, natural language). Here we illustrate the composition systems and the experiments we did with hand-written character.

  • ボルツマンマシンと自己組織化

    伊達 章, 倉田耕治

    Clinical Neuroscience   34   885 - 888   2016.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • ボルツマンマシンと自己組織化 Invited

    伊達 章,倉田 耕治

    Clinical Neuroscience   34   885 - 888   2016.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

display all >>

Books 【 display / non-display

  • Brain Processes, Theories and Models

    Akira Date, Koji Kurata, Shun-ichi Amari( Role: Joint author)

    The MIT Press(Cambridge, Massachusetts)全562頁(分担)274- 283頁  1995.11 

     More details

    Language:English Book type:Scholarly book

MISC 【 display / non-display

  • On the composition systems and their application to handwritten character recognition

    伊達 章, 窪田 光, 山田 雄輔

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   116 ( 259 )   19 - 24   2016.10

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (bulletin of university, research institution)   Publisher:電子情報通信学会  

    researchmap

  • 参加者の声(シーサートワークショップ in 宮崎 2016) Invited

    伊達 章

    日本シーサート協議会 地区活動タスクフォース   2016.9

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:日本シーサート協議会  

  • ずうずうしい学生

    伊達 章

    宮下保司教授東京大学退職記念誌   77 - 78   2015.3

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (other)   Publisher:東京大学医学部統合生理学教室  

  • 自己組織神経回路モデルによる情報表現の獲得

    伊達 章

    Telecom Frontier   ( 81 )   1 - 9   2013.11

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:一般財団法人 テレコム先端技術研究支援センター  

  • On the self-organization of topographic mapping in Boltzmann machines

    DATE Akira, KURATA Koji

    IEICE technical report. Neurocomputing   112 ( 480 )   203 - 208   2013.3

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (bulletin of university, research institution)   Publisher:The Institute of Electronics, Information and Communication Engineers  

    We propose a learning algorithm for Boltzmann neural fields [1] developed by Kurata (1988). The Boltzmann machine learning algorithm is theoretically elegant and easy to implement in hardware but very slow in networks with interconnected hidden units. This definitive deficit has been overcome in part by G.E. Hinton et al. for Boltzmann machines with a bipartite graph structure [2-5]. A two-layer model of Boltzmann neural field developed by Kurata (1988) has similar structure but there are connections within a second (hidden) layer. Since it does not have a bipartite graph structure, we could not apply Hinton's learning algorithm. By putting a constraint that only local excitation pattern appears in the output layer, we have developed a learning algorithm without running all units stochastically. Now we can follow the learning dynamics of connections between units.

    researchmap

display all >>

Presentations 【 display / non-display

  • A self-organization model developing higher order units by self-test learning International conference

    Akira Date, Shunsuke Hanai

    The 5th CiNet Conference: Computation and representation in brains and machinesAkira  (Osaka)  National Institute of Information and Communications Technology

     More details

    Event date: 2019.2.20 - 2019.2.22

    Language:English   Presentation type:Poster presentation  

    Venue:Osaka  

    We have carried out computer simulation studies of a Geman-Davis selforganizing network model in which the number of units increases with time. The purpose of the network is to discover regularities in a task domain.
    To investigate the model, we have applied it to a classical 8 by 8 image world in which random horizontal and vertical lines are presented. Here we show the ability of the model to create useful internal representation. This model was proposed a few yares before the inventions of Boltzmann machine and Markov random field formalisms for capturing complex environments. We think it has a lot of interesting properties to study further.

  • 自己テストにより高次素子を追加し学習する自己組織化モデル

    伊達 章, 花井 俊介

    第21回情報論的学習理論ワークショップ  (北海道札幌市)  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2018.11.5

    Language:Japanese   Presentation type:Poster presentation  

    Venue:北海道札幌市  

    researchmap

  • Experiments of a self-organization machine discovering regularities in high-dimensional environment International conference

    Akira Date, Shunsuke Hanai

    Champalimaud Research Symposium, Quantitative approaches to Behaviour and Neural Systems 

     More details

    Event date: 2018.10.25

    Language:English   Presentation type:Poster presentation  

    researchmap

  • 私の考える ICT利活用促進

    伊達 章

    みやざき新産業創出研究会 ICT利活用促進分科会 

     More details

    Event date: 2016.12.12

    Language:Japanese   Presentation type:Oral presentation (general)  

  • 構成性システムとその手書き文字認識への応用について

    伊達 章,窪田 光, 山田 雄輔,

    電子情報通信学会 パターン認識・メディア理解研究会  (宮崎大学)  電子情報通信学会

     More details

    Event date: 2016.10.20 - 2016.10.21

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:宮崎大学  

display all >>

Industrial property rights 【 display / non-display

  • ロボットの位置および向きの情報の自己組織的学習処理方法ならびにその学習処理システム、およびその学習プログラム

    伊達 章、倉田 耕治

     More details

    Applicant:独立行政法人情報通信研究機構

    Application no:特許出願2003-414118  Date applied:2003.12.12

    Announcement no:特許公開2005-174040  Date announced:2005.6.30

    Patent/Registration no:特許第3826197号  Date registered:2006.7.14 

    Country of applicant:Domestic  

Grant-in-Aid for Scientific Research 【 display / non-display

  • 自己組織神経回路モデルによる情報表現の形成

    2014.04 - 2018.03

    科学研究費補助金  基盤研究(C)

      More details

    Authorship:Principal investigator 

    いくつか基本的な自己組織のモデルの性質を解析し,なぜ精度の高い機械が実現できるのか,その手がかりを得る.

  • 高次元データに対する事後確率分構造の解析

    2010.04 - 2014.03

    科学研究費補助金  基盤研究(C)

      More details

    Authorship:Principal investigator 

    高次元データに対する事後確率分の構造について研究を実施する.

  • 連想記憶モデルを用いた海馬新生ニューロンの情報論的研究

    2007.04 - 2010.03

    科学研究費補助金  基盤研究(C)

      More details

    Authorship:Principal investigator 

    連想記憶モデルを用いた海馬新生ニューロンの情報論的研究

  • 視覚入力から位置と向きの情報を分離する自己組織化モデルに関する研究

    2004.04 - 2007.03

    科学研究費補助金  若手研究(B)

      More details

    Authorship:Principal investigator 

    視覚入力から位置と向きの情報を分離する自己組織化モデルに関する研究

  • 階層型マルコフ確率場による画像情報処理

    2002.04 - 2004.03

    科学研究費補助金  若手研究(B)

      More details

    階層型マルコフ確率場による画像情報処理

display all >>