SHIBATA Katsunari 柴田克成

… Alternative Names

柴田克成シバタカツナリ

Less

Researcher Number	10260522
External Links
Affiliation (based on the past Project Information) *help	2019 – 2020: 大分大学, 理工学部, 教授 2017 – 2018: 大分大学, 理工学部, 准教授 2015 – 2016: 大分大学, 工学部, 准教授 2007 – 2013: Oita University, 工学部, 准教授 2001 – 2006: 大分大学, 工学部, 助教授 1994 – 1996: 東京大学, 先端科学技術研究センター, 助手
Review Section/Research Field	Principal Investigator Perception information processing/Intelligent robotics / Intelligent informatics / Basic Section 61040:Soft computing-related / Intelligent robotics Except Principal Investigator Control engineering / 計測・制御工学 / 電子デバイス・機器工学
Keywords	Principal Investigator ニューラルネット / 強化学習 / 知能創発 / リカレントニューラルネット / 自律学習 / カオスニューラルネット / 感度 / ダイナミック強化学習 / 決定論的探索 / コミュニケーション … More / ロボット / 因果トレース / 時間的抽象化 / 空間的抽象化 / 乗算ニューロン / 探索 / 予測 / シンボル / コミュニケーション学習 / 高次機能 / 知能ロボット / 視覚センサ / 多段階状態遷移 / 思考創発 / カオス性 / エッジオブカオス / 感度調整学習（SAL) / 高次探索 / 符号付き因果トレース / BPWT / リザバー / カオスニューロン / 障害物回避 / 不応性 / 誤差逆伝播法 / カオス生成・維持学習 / 内部ダイナミクス / 深層学習 / 勾配消失問題 / リアプノフ指数 / カオスダイナミクス / 汎用人工知能 / ダイナミクス / 思考 / 感度調整学習 / Emergence of Intelligence / Temporal Abstraction / Intelligent Exploration / Spatial Abstraction / Robot / Symbol / Recurrent Neural Network / Reinforcement Learning / 隠れニューロン / 成長型ニューラルネット / カラー情報処理 / シンボルグラウンディング問題 / 知能形成 / 実用的リカレント学習(PRL) / 報酬期待ニューロン / ゲートニューロン / 一様探索 / 文脈 / 抽象化 / 知的探索 / 時間軸 / 動詞表現獲得 / 時間軸調整 / 微分型トレース / 自律的役割分担 / 離散的・抽象的表現 / 動詞表現 / 概念形成 / シンボル処理創発 / 決定論的知的探索 / 離散状態遷移 / 合目的性 / 意味付け / 記憶 / 高次機能創発 / 色の恒常性 / 適正度の履歴 / エッジ画像 / 大域的表現 / 中間層 / 実ロボット / 創発 / 押し動作 / 移動ロボット / Direct-Vision-Based強化学習 / 中間層ニューロン / 時間軸スムージング学習 / 時間変化量一低化学習 / 視覚センサ信号 / 局所センサ信号統合化学習 / 空間情報の時間的滑らかさ / 障害回避 … More Except Principal Investigator ニューラルネットワーク / 時系列 / モデレ-ショニズム / YBCO / brain nervous system / sensorimotor mapping / internal model / dynamic environment / motor adaptation / 自己組織化 / ロボティクス / 生体システム / 環境認知モデル / 上肢到達運動 / 拘束ダイナミクス / 運動制御 / 運動学習 / 適応行動 / 身体自由度 / 身体ダイナミクス / 感覚・運動統合 / Wave-field information processing / Neural device / Complex-valued neural network / Optical information processing / Coherence / Neural hardware / Parallel information processing / Neural network / カオス / リアプノフ指数 / リカレントネットワーク / 周波数領域並列化 / バックプロパゲーション学習 / 汎化特性 / コヒーレント型ニューラルネットワーク / 波動情報処理 / ニューロデバイス / 複素ニューラルネットワーク / 光情報処理 / コヒーレンス / ニューロハードウエア / 並列情報処理 / YBaCuO / Co-planar / Focused Ion Beam / ジョセフソン接合 / 酸化物高温超伝導体 / 収束イオンビーム / 高温超伝導 / 共プレーナ型 / ジョセフソン素子 / FIB / パルス伝送 / パルスニューロン / 眼球運動 / 反射弓 / 教師なし学習 / 電界効果 / 超伝導3端子素子 / 縮退半導体 / 半導体バンド伝導 / ポッピング伝導 / PYBCO / PBCO Less

Establishment of Chaos-based Dynamic Reinforcement Learning as Taking an Essential Technology to Realize Emergence of Thinking in AdvancePrincipal Investigator
- Principal Investigator
  
  柴田克成
- Project Period (FY)
  2020
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 61040:Soft computing-related
- Research Institution
  Oita University
From "Exploration" To "Thinking" - Development of Chaos Dynamics through Reinforcement LearningPrincipal Investigator
- Principal Investigator
  
  SHIBATA Katsunari
- Project Period (FY)
  2015 – 2019
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent robotics
- Research Institution
  Oita University
Exploration of a Breakthrough Technology for Emergence of Symbol Processing by Neuro-based Reinforcement Learning Considering Time AxisPrincipal Investigator
- Principal Investigator
  
  SHIBATA Katsunari
- Project Period (FY)
  2011 – 2013
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Oita University
A challenge towards how far the emergence of higher functions can be explained by reinforcement learning using a neural networkPrincipal Investigator
- Principal Investigator
  
  SHIBATA Katsunari
- Project Period (FY)
  2007 – 2010
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Oita University
Autonomous, Harmonious and Purposive Acquisition of Various Functions of Robots by Reinforcement Learning and the Relation to the Intelligence FormationPrincipal Investigator
- Principal Investigator
  
  SHIBATA Katsunari
- Project Period (FY)
  2003 – 2006
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Oita University
Study on Body Dynamics Formation and Pattern Generation for Motor/Action Learning
- Principal Investigator
  
  ITO Koji
- Project Period (FY)
  2002 – 2005
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Research Field
  
  Control engineering
- Research Institution
  Tokyo Institute of Technology
実ロボットによるDirect-Vision-Based強化学習の検証Principal Investigator
- Principal Investigator
  
  柴田克成
- Project Period (FY)
  2001 – 2002
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  Oita University
センサ信号統合化学習と強化学習の融合に関する研究Principal Investigator
- Principal Investigator
  
  柴田克成
- Project Period (FY)
  1996
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Research Institution
  The University of Tokyo
時間的情報を考慮したニューラルネットモデルの学習に関する基礎的研究
- Principal Investigator
  
  岡部洋一
- Project Period (FY)
  1996
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Research Institution
  The University of Tokyo
Coherent neural networks : Construction of prototypal subsystems
- Principal Investigator
  
  HIROSE Akira
- Project Period (FY)
  1996 – 1997
- Research Category
  
  Grant-in-Aid for Scientific Research (A)
- Research Field
  
  計測・制御工学
- Research Institution
  The University of Tokyo
パルス型ニューロデバイスのためのニューラルネットモデルに関する基礎的研究
- Principal Investigator
  
  岡部洋一
- Project Period (FY)
  1995
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Research Institution
  The University of Tokyo
評価と動作の並列学習により障害回避を自己形成する自律能動学習機械の研究Principal Investigator
- Principal Investigator
  
  柴田克成
- Project Period (FY)
  1995
- Research Category
  
  Grant-in-Aid for Encouragement of Young Scientists (A)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
Fabrication of High-Tc Superconducting Co-planar Josephson Junctions Using Focused Ion Beam
- Principal Investigator
  
  OKABE Yoichi
- Project Period (FY)
  1995 – 1997
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Research Field
  
  電子デバイス・機器工学
- Research Institution
  The University of Tokyo
酸化物超伝導体/酸化物半導体の界面構造及びジョセフソン素子応用に関する研究
- Principal Investigator
  
  OKABE Yoichi
- Project Period (FY)
  1994
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Research Institution
  The University of Tokyo
環境とのやりとりにより動作制御を獲得するニューラルネットワーク
- Principal Investigator
  
  岡部洋一
- Project Period (FY)
  1994
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Research Institution
  The University of Tokyo

[Book] Emergence of Intelligence through Reinforcement Learning with a Neural Network(Advances in Reinforcement Learning, InTech)(Abdelhamid Mellouk (Ed.))2011
- Author(s)
  柴田克成
- Data Source
  KAKENHI-PROJECT-19300070
[Book] 「ロボット情報学ハンドブック」(第7.5節ニューラルネットワークのみ)2010
- Author(s)
  柴田克成
- Total Pages
  13
- Publisher
  ナノオプトニクスエナジー
- Data Source
  KAKENHI-PROJECT-19300070
[Book] ニューラルネットワーク(「ロボット情報学ハンドブック」,ナノオプトニクスエナジー,第7.5節)2010
- Author(s)
  柴田克成
- Data Source
  KAKENHI-PROJECT-19300070
[Book] Advances in Reinforcement Learning2010
- Author(s)
  Katsunari Shibata
- Publisher
  InTech
- Data Source
  KAKENHI-PROJECT-19300070
[Book] ニューラルネットワーク計算知能(第12章ニューラルネットを用いた強化学習とロボットの知能)2006
- Author(s)
  柴田克成, 岡部洋一, 伊藤宏司
- Total Pages
  22
- Publisher
  森北出版
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 層構造リカレントネットにおける感度調整学習時の感度と最大リアプノフ指数の関係2021
- Author(s)
  江島拓哉, 徳丸侑輝, 柴田克成
- Journal Title
  
  電子情報通信学会技術研究報告
  
  Volume: Vol.120, No. 403 Pages: 151-156
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] カオスニューラルネットを用いた記憶問題の学習における不応性導入の影響2020
- Author(s)
  黒崎耕平, 柴田克成
- Journal Title
  
  第39回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 126-129
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] Q-learning with exploration driven by internal dynamics in chaotic neural network2020
- Author(s)
  Toshitaka Matsuki and Katsunari Shibata
- Journal Title
  
  Proc. of Int'l Joint Conf. on Neural Networks (IJCNN) 2020
  
  Volume: - Pages: 1-7
- DOI
  10.1109/ijcnn48605.2020.9207114
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] リカレントネットにおける感度調整学習時の感度とリアプノフ指数の関係2020
- Author(s)
  江島拓哉, 徳丸侑輝, 柴田克成
- Journal Title
  
  第39回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 118-121
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] 感度調整学習を用いたリザバネットの構築2020
- Author(s)
  吉岡晴海, 松木俊貴, 柴田克成
- Journal Title
  
  第39回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 122-125
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] リカレントネット内の感度調整によって学習を行う強化学習2020
- Author(s)
  徳丸侑輝, 柴田克成
- Journal Title
  
  第39回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 160-163
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning2020
- Author(s)
  Toshitaka Matsuki and Katsunari Shibata
- Journal Title
  
  Neural Networks
  
  Volume: 132 Pages: 19-29
- DOI
  10.1016/j.neunet.2020.08.002
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] リカレントネットによる状態遷移タスクの教師あり学習におけるカオス性の影響2020
- Author(s)
  大石将人,松木俊貴, 柴田克成
- Journal Title
  
  第39回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 156-159
- Data Source
  KAKENHI-PROJECT-20K11993
[Journal Article] Chaos-Based Reinforcement Learning When Introducing Refractoriness in Each Neuron2019
- Author(s)
  Katsuki Sato and Katsunari Shibata
- Journal Title
  
  In: Kim JH., Myung H., Lee SM. (eds) Robot Intelligence Technology and Applications. RiTA 2018. Communications in Computer and Information Science
  
  Volume: 1015 Pages: 76-84
- DOI
  10.1007/978-981-13-7780-8_7
- ISBN
  9789811377792, 9789811377808
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Learning Time Constant of Continuous-Time Neurons with Gradient Descent2019
- Author(s)
  Matsuki Toshitaka, Shibata Katsunari
- Journal Title
  
  In: P. P. Abdul Majeed A., Mat-Jizat J., Hassan M., Taha Z., Choi H., Kim J. (eds) RITA 2018. Lecture Notes in Mechanical Engineering. Springer
  
  Volume: - Pages: 149-159
- DOI
  10.1007/978-981-13-8323-6_13
- ISBN
  9789811383229, 9789811383236
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットを用いた記憶タスクの強化学習におけるカオス性の影響2019
- Author(s)
  大石将人, 柴田克成
- Journal Title
  
  第38回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 83-86
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] リカレントネットにおける感度調整学習でのカオスダイナミクスの生成と維持2019
- Author(s)
  徳丸侑輝, 柴田克成
- Journal Title
  
  第38回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 75-78
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] 多層ニューラルネットにおける勾配消失問題解決法としての感度調整学習2019
- Author(s)
  長谷部圭亮, 柴田克成
- Journal Title
  
  第38回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 87-90
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] 多層リードアウトを持つリザバを用いた強化学習におけるネットワーク構造の検討2019
- Author(s)
  吉岡晴海, 松木俊貴, 柴田克成
- Journal Title
  
  第38回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 79-82
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout2018
- Author(s)
  Matsuki Toshitaka、Shibata Katsunari
- Journal Title
  
  In: Kim JH. et al. (eds) Robot Intelligence Technology and Applications 5. RiTA 2017. Advances in Intelligent Systems and Computing
  
  Volume: 751 Pages: 17-26
- DOI
  10.1007/978-3-319-78452-6_2
- ISBN
  9783319784519, 9783319784526
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] New Reinforcement Learning Using a Chaotic Neural Network for Emergence of “Thinking”2017
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] 深層学習が示唆するend-to-end強化学習に基づく機能創発アプローチの重要性と思考の創発に向けたカオスニューラルネットを用いた新しい強化学習2017
- Author(s)
  柴田克成，後藤祐樹
- Journal Title
  
  認知科学
  
  Volume: 24巻，1号 Pages: 96-117
- NAID
  130006038535
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットを用いた強化学習における不応性を有するカオスニューロンの導入2017
- Author(s)
  佐藤克樹, 後藤祐樹, 柴田克成
- Journal Title
  
  第36回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 109-112
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Influence of the Chaotic Property on Reinforcement Learning Using a Chaotic Neural Network2017
- Author(s)
  Yuki Goto, Katsunari Shibata
- Journal Title
  
  Proc. of Int'l Conf. on Neural Information Processing (ICONIP)2017, LNCS 10634
  
  Volume: - Pages: 759-767
- DOI
  10.1007/978-3-319-70087-8_78
- ISBN
  9783319700861, 9783319700878
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Functions that Emerge through End-to-end Reinforcement Learning - The Direction for Artificial General Intelligence -2017
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Communications that Emerge through Reinforcement Learning Using a (Recurrent) Neural Network2017
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットの内部ダイナミクスを利用した記憶タスクの報酬に基づく学習2017
- Author(s)
  松木俊貴, 柴田克成
- Journal Title
  
  第36回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 101-104
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットを用いた強化学習におけるカオス性の影響2017
- Author(s)
  後藤祐樹, 柴田克成
- Journal Title
  
  第36回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 97-100
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] ニューラルネットワークを使った強化学習による行動学習を通した音声認識機能の創発2017
- Author(s)
  江越正大, 柴田克成
- Journal Title
  
  第36回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 129-132
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] BPWT を用いたリカレントネットの教師あり学習における相互結合部の重み値の影響2016
- Author(s)
  山本一真，柴田克成
- Journal Title
  
  第32回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 128-131
- Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットを用いた強化学習における高次探索の創発2016
- Author(s)
  後藤祐樹，柴田克成
- Journal Title
  
  第32回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 120-123
- Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Emergence of Higher Exploration in Reinforcement Learning Using a Chaotic Neural Network2016
- Author(s)
  Yuki Goto and Katsunari Shibata
- Journal Title
  
  Proc. of Int'l Conf. on Neural Information Processing (ICONIP)2016, LNCS 9947
  
  Volume: - Pages: 40-48
- DOI
  10.1007/978-3-319-46687-3_5
- ISBN
  9783319466866, 9783319466873
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] カオスニューラルネットの内部ダイナミクスを利用した記憶タスクの報酬に基づく学習2016
- Author(s)
  松木俊貴，柴田克成
- Journal Title
  
  第32回計測自動制御学会九州支部学術講演会予稿集
  
  Volume: - Pages: 124-127
- Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network2016
- Author(s)
  Toshitaka Matsuki and Katsunari Shibata
- Journal Title
  
  Proc. of Int'l Conf. on Neural Information Processing (ICONIP)2016, LNCS 9947
  
  Volume: - Pages: 376-383
- DOI
  10.1007/978-3-319-46687-3_42
- ISBN
  9783319466866, 9783319466873
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] Reinforcement Learning with Internal-Dynamics-based Exploration Using a Chaotic Neural Network2015
- Author(s)
  Katsunari Shibata and Yuta Sakashita
- Journal Title
  
  Proc. of Int'l Joint Conf. on Neural Networks (IJCNN)2015
  
  Volume: -
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] 動的ニューロンモデルを用いたニューラルネットワークへの因果トレースの適用2015
- Author(s)
  山本一真，柴田克成
- Journal Title
  
  第２５回インテリジェント・システム・シンポジウム論文集
  
  Volume: - Pages: 136-141
- Data Source
  KAKENHI-PROJECT-15K00360
[Journal Article] 因果トレース - 並列かつ主観的時間スケールの導入による過去の処理の効率的学習 -2014
- Author(s)
  柴田克成
- Journal Title
  
  電子情報通信学会技術報告
  
  Volume: NC2013 Pages: 157-162
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] 予測を要して連続動作を含む柔軟な行動のActor-Q学習による獲得2013
- Author(s)
  柴田克成, 後藤健太
- Journal Title
  
  第23回インテリジェント・システム・シンポジウム (FAN 2013) 講演論文集
  
  Pages: 86-91
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] 強化学習によるリカレントニューラルネットワーク内部での振動子創発の可能性2013
- Author(s)
  品矢裕介, 柴田克成
- Journal Title
  
  第32回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 74-77
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] RNNを用いた強化学習によるセンサ信号の時間変化を表すコミュニケーションの創発2013
- Author(s)
  朱祺, 柴田克成
- Journal Title
  
  第32回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 71-74
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Flexible Prediction-Based Discrete Decision Making and Continuous Motion Generation through Actor-Q-Learning2013
- Author(s)
  Katsunari Shibata and Kenta Goto
- Journal Title
  
  Proc. of Int'l Conf. on Development and Learning and on Epigenetic Robotics (ICDL-Epirob)
  
  Volume: ID 15 (CDROM)
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Flexible Prediction-Based Discrete Decision Making and Continuous Motion Generation through Actor-Q-Learning2013
- Author(s)
  Katsunari Shibata and Kenta Goto
- Journal Title
  
  Proc. of Int'l Conf. on Development and Learning and on Epigenetic Robotics (ICDL-Epirob) 2013
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] ニューラルネットを用いた強化学習による行動の学習を通した色恒常性の創発2013
- Author(s)
  柴田克成, 栗崎俊介
- Journal Title
  
  電子情報通信学会技術報告
  
  Volume: NC2012-134 - NC2012-182 Pages: 215-220
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] リカレントネットを用いた強化学習における離散的かつ抽象的な状態表現の創発2012
- Author(s)
  沢津橋由人, Mohamad Faizal Bin Samusudin, 柴田克成
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会講演論文集
  
  Volume: 1 Pages: 402-407
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Discrete and Abstract State Representation in Continuous Input Task through Reinforcement Learning2012
- Author(s)
  Yoshito Sawatsubashi, Mohamad Faizal bin Samsudin and Katsunari Shibata
- Journal Title
  
  Advances in Intelligent Systems and Computing, Robot Intelligence Technology and Applications 2012, Proc. of RiTA 2012
  
  Volume: 1 Pages: 13-22
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Color Constancy Illusion through Reinforcement Learning with a Neural Network2012
- Author(s)
  Katsunari Shibata and Shunsuke Kurizaki
- Journal Title
  
  Proc. of ICDL-EpiRob (Int'l Conf. on Development and Learning- Epigenetic Robotics)
  
  Pages: 1-6
- DOI
  10.1109/devlrn.2012.6400580
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Differential Trace in Learning of Value Function with a Neural Network, Advances in Intelligent Systems and Computing, Robot Intelligence Technology and Applications 20122012
- Author(s)
  Katsunari Shibata and Shuji Enoki
- Journal Title
  
  Proc. of RiTA
  
  Volume: 55-64
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Mohamad Faizal bin Samsudin and Katsunari Shibata, Emergence of Discrete and Abstract State Representation in Continuous Input Task through Reinforcement Learning, Advances in Intelligent Systems and Computing, Robot Intelligence Technology and Applications 20122012
- Author(s)
  Yoshito Sawatsubashi, Mohamad Faizal bin Samsudin and Katsunari Shibata
- Journal Title
  
  Proc. of RiTA
  
  Volume: 13-22
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Multi-Step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network2012
- Author(s)
  Mohamad Faizal bin Samsudin, Yoshito Sawatsubashi and Katsunari Shibata
- Journal Title
  
  LNCS(Lecture Notes in Computer Science), Neural Information Processing, Proc. of ICONIP2012
  
  Volume: 1 Pages: 583-590
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Multi-Step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network2012
- Author(s)
  Mohamad Faizal bin Samsudin, Yoshito Sawatsubashi and Katsunari Shibata
- Journal Title
  
  LNCS(Lecture Notes in Computer Science), Neural Information Processing, Proc. of ICONIP (Int'l Conf. on Neural Information Processing)
  
  Volume: 7664 Pages: 583-590
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] ニューラルネットを用いた価値関数の学習における微分型トレースの提案2012
- Author(s)
  榎修志, 柴田克成
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会講演論文集
  
  Volume: 1 Pages: 396-401
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Differential Trace in Learning of Value Function with a Neural Network2012
- Author(s)
  Katsunari Shibata and Shuji Enoki
- Journal Title
  
  Advances in Intelligent Systems and Computing, Robot Intelligence Technology and Applications 2012, Proc. of RiTA 2012
  
  Volume: 1 Pages: 55-64
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] 強化学習による合目的的かつ接地した一方向コミュニケーションの創発2012
- Author(s)
  柴田克成, 笹原冬月
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会講演論文集
  
  Volume: 1 Pages: 390-395
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Purposive and Grounded Communication through Reinforcement Learning, LNCS(Lecture Notes in Computer Science)2011
- Author(s)
  Katsunari Shibata and Kazuki Sasahara
- Journal Title
  
  LNCS(Lecture Notes in Computer Science), Vol. 7064, Proc. of ICONIP (Int'l Conf. on Neural Information Processing)
  
  Volume: 7064 Pages: 66-75
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] リカレントネットを用いた強化学習による探索行動と多値記憶の創発2011
- Author(s)
  柴田克成, 後藤健太
- Journal Title
  
  電子情報通信学会技術報告
  
  Volume: -
- NAID
  110009546290
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Discovery of Pattern Meaning from Delayed ...2011
- Author(s)
  Katsunari Shibata & Hiroki Utsunomiya
- Journal Title
  
  Proc. of Int'l Joint Conf. on Neural Networks 2011
  
  Volume: - Pages: 1445-1452
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] 画像を入力とするニューラルネットの学習における方位選択性入力の付加2011
- Author(s)
  沢津橋由人, 柴田克成
- Journal Title
  
  第30回SICE九州支部学術講演会予稿集
  
  Volume: - Pages: 151-154
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] リカレントネットによる内部状態遷移を要する問題学習時の初期重み値の影響2011
- Author(s)
  田口優馬, 柴田克成
- Journal Title
  
  第30回SICE九州支部学術講演会予稿集
  
  Volume: - Pages: 87-90
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Context-based Word Recognition through ...2011
- Author(s)
  Ahmad Afif Mohd Faudzi & Katsunari Shibata
- Journal Title
  
  第30回SICE九州支部学術講演会予稿集
  
  Volume: - Pages: 155-158
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Emergence of Purposive and Grounded ...2011
- Author(s)
  Katsunari Shibata and Kazuki Sasahara
- Journal Title
  
  LNCS(Lecture Notes in Computer Science)
  
  Volume: Vol. 7064 Pages: 66-75
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Discount and Speed/Execution tradeoffs in ...2011
- Author(s)
  R. Uribe, F. Lozanom, K. Shibata & C. Anderson
- Journal Title
  
  Proc. of IEEE Conf. on CIG 2011
  
  Volume: - Pages: 79-86
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-23500245
[Journal Article] Learning of Camera Motion and Object Recognition Using Actor-Q Architecture2010
- Author(s)
  Armad Afif Mohd Faudi, Katsunari Shibata
- Journal Title
  
  Proc.of SICE Annual Conf.2010
  
  Volume: (CD-ROM)
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Emergence of prediction by reinforcement learning using a recurrent neural network2010
- Author(s)
  Kenta Goto, Katsunari Shibata
- Journal Title
  
  Journal of Robotics
  
  Volume: 2010
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Deterministic Exploration and Purposive Memory through Reinforcement Learning with a Recurrent Neural Network2010
- Author(s)
  Kenta Goto, Katsunari Shibata
- Journal Title
  
  Proc.of SICE Annual Conf. 2010
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Deterministic Exploration and Purposive Memory throuh Reinforcement Learning with a Recurrent Neural Network2010
- Author(s)
  Kenta Goto, Katsunari Shibata
- Journal Title
  
  Proc.of SICE Annual Conf.2010
  
  Volume: (CD-ROM)
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Emergence of prediction by reinforcement learning using a recurrent neural network2010
- Author(s)
  Kenta Goto, Katsunari Shibata
- Journal Title
  
  Journal of Robotics Vol.2010
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Learning of Action Generation from Raw Camera Images in a Real-World-like Environment by Simple Coupling of Reinforcement Learning and a Neural Network2009
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Journal Title
  
  Advances in Neuro-Information Processing, Lecture Notes in Computer Science 5506
  
  Pages: 755-762
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Improvement of Practical Recurrent Learning Method and Application to a Pattern Classification Task2009
- Author(s)
  Mohamad Faizal Bin Samsudin, Katsunari Shibata
- Journal Title
  
  Advances in Neuro-Information Processing, Lecture Notes in Computer Science 5507
  
  Pages: 631-638
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Flexible Image Recognition by Coupling of Reinforcement Learning and a Neural Network2009
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Journal Title
  
  SICE Journal of Control, Measurement, and System Integration (JCMSI) Vol.2, No.2
  
  Pages: 122-129
- NAID
  10031152631
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Contextual Behavior and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task2009
- Author(s)
  Hioroki Utsunomiya, Katsunari Shibata
- Journal Title
  
  Lecture Notes in Computer Science Vol.5507
  
  Pages: 970-978
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Contextual Behavior and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task2009
- Author(s)
  Hioroki Utsumomiya, Katsunari Shibata
- Journal Title
  
  Advances in Neuro-Information Processing, Lecture Notes in Computer Science 5507
  
  Pages: 970-978
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Effect of number of hidden neurons on learning in large-scale layered neural networks2009
- Author(s)
  Katsunari Shibata, Yusuke Ikeda
- Journal Title
  
  Proc.of ICCAS-SICE(ICROS-SICE Int'l Joint Conf.)2009
  
  Pages: 5008-5013
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Learning of Action Generation from Raw Camera Images in a Real-World-like Environment by Simple Coupling of Reinforcement Learning and a Neural Network2009
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Journal Title
  
  Advances in Neuro-Information Processing, Lecture Notes in Computer Science Vol.5506
  
  Pages: 755-762
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Flexible Image Recognition by Coupling of Reinforcement Leaming and a Neural Network2008
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Journal Title
  
  SICE Journal of Control, Measurement, and System Integration (JCMSI) Vol. 2, No. 2
  
  Pages: 122-129
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Practical Recurrent Learning (PRL)in the Discrete Time Domain2008
- Author(s)
  Mohamad Faizal Bin Samsudin, Takeshi. Hirose, Katsunari. Shibata
- Journal Title
  
  Neural Information Processing of Lecture Notes in Computer Science, (Proc. of Intl Conf. on Neural Information Processing System) Vol. 4984
  
  Pages: 228-237
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] 強化学習により対象物検出行動を学習した画像入力ニューラルネットにおける中間層ニューロンの解析2008
- Author(s)
  柴田克成, 河野友彦
- Journal Title
  
  第18回インテリジェント・システム・シンポジウム(FAN2008)講演予稿集
  
  Pages: 145-150
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Flexible Image Recognition by Coupling of Reinforcement Learning and a Neural Network2008
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Journal Title
  
  SICE Journal of Control, Measurement, and System Integration (JCMSI) Vol.2, No.2
- NAID
  10031152631
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] リカレントネットを用いた強化学習による記憶を利用した探索行動の学習2008
- Author(s)
  後藤健太, 柴田克成
- Journal Title
  
  第61回電気関係学会九州支部連合大会講演論文集 (CD-ROM)
- NAID
  130005033184
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] 階層型ニューラルネットにおける中間層ての適応的空間再構成と中間層レベルの汎化に基づく知識の継承2007
- Author(s)
  柴田克成, 伊藤宏司
- Journal Title
  
  計測自動制御学会論文集 Vol. 43, No.1
  
  Pages: 54-63
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 階層型ニューラルネットにおける中間層での適応的空間再構成と中間層レベルの汎化に基づく知識の継承2007
- Author(s)
  柴田克成, 伊藤宏司
- Journal Title
  
  計測自動制御学会論文集 Vol.43, No.1
  
  Pages: 54-63
- NAID
  10018479914
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Practical Recurrent Learning (PRL) in the Discrete Time Domain2007
- Author(s)
  Mohamad Faizal Bin Samsudin, Takeshi. Hirose, Katsunari. Shibata
- Journal Title
  
  Proc. of Int'l Conf. on Neural Information Processing System (CD-ROM)
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] リカレント型ニューラルネットの実用的な学習則である離散時間PRL学習法2007
- Author(s)
  Mohamad Faizal Bin Samsudin, 廣瀬武志, 柴田克成
- Journal Title
  
  第26回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 57-60
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] 複数の隠れニューロンの生成が可能な成長型ニューラルネットの構築2007
- Author(s)
  由崎高志, 柴田克成
- Journal Title
  
  第26回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 53-56
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] 画像入カニューラルネットを用いた強化学習による可動カメラの対象物検出行動2007
- Author(s)
  河野友彦, 幸和芳, 柴田克成
- Journal Title
  
  第26回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 155-158
- Data Source
  KAKENHI-PROJECT-19300070
[Journal Article] Acquisition of Deterministic Exploration Behavior by Reinforcement Learning2006
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc.of the 11th Int'l Symp.on Artificial Life and Robotics CD-ROM
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Spatial Abstraction and Knowledge Transfer in Reinforcement Learning Using a Multi-Layer Neural Network2006
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of ICDL5 (Fifth Int'l Conf. on Development and Learning) (CD-ROM)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] A Model to Explain the Emergence of Reward Expectancy neurons using Reinforcement Learning and Neural Network2006
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Neurocomputing Vol. 69
  
  Pages: 1327-1331
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Acquisition of Deterministic Exploration Behavior by Reinforcement Learning2006
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of the 11th Int'l Symp. on Artificial Life and Robotics (AROB) (CD-ROM)
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Acquisition of Deterministic Exploration Behavior by Reinforcement Learning2006
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of the 11th Int'l Symp. on Artificial Life and Robotics (CD-ROM)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] A Model to Explain the Emergence of Reward Expectancy neurons using Reinforcement Learning and Neural Network2006
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Neurocomputing Vol.69
  
  Pages: 1327-1331
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Learning of Deterministic Exploration and Temporal Abstraction in Reinforcement Learning2006
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc. of SICE-ICCAS (SICE-ICASE Int'l Joint Conf.) (CD-ROM)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] A model of emergence of reward expectancy neurons by reinforcement learning2005
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Proc.of 10^<th> Int'l Symp.On Artificial Life and Robotics (AROB) CD-ROM
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] An Explanation of Emergence of Reward Expectancy Neurons Usine Reinforcement Learning and Neural Net2005
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Abstract Book of Fourteenth Annual Computational Neuroscience Meeting
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 強化学習による探索行動の学習2005
- Author(s)
  柴田克成
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会2005講演論文集
  
  Pages: 11-16
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Discretization of Series of Communication Signals in Noisy Environment by Reinforcement Learning2005
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Proc.of the 7th Int'l Conf.in Adaptive and Natural Computing Algorithms
  
  Pages: 486-489
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Effect of action selection on emergence of one-way communication using Q-learning2005
- Author(s)
  Masanobu Nakanishi, Katsunari Shibata
- Journal Title
  
  Proc. of 10^<th> Int'l Symp. On Artificial Life and Robotics (AROB)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] A model of emergence of reward expectancy neurons by reinforcement learning2005
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Proc. of 10^<th> Int'l Symp. On Artificial Life and Robotics (AROB)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Effect of Action Selection on Emergence of One-way Communication Using Q-]earning2005
- Author(s)
  Masanobu Nakanishi, Katsunari Shibata
- Journal Title
  
  Proc. of the 10th Int'l Symp. on Artificial Life and Robotics (AROB). (CD-ROM)
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Effect of action selection on emergence of one-way communication using Q-learning2005
- Author(s)
  Masanobu Nakanishi, Katsunari Shibata
- Journal Title
  
  Proc.of 10^<th> Int'l Symp.On Artificial Life and Robotics (AROB) CD-ROM
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] An Explanation of Emergence of Reward Expectancy Neurons Using Reinforcement Learning and Neural Net2005
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Abstract Book of Fourteenth Annual Computational Neuroscience Meeting
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] A Model of Emergence of Reward Expectancy neurons by Reinforcement Learning2005
- Author(s)
  Shinya Ishii, Munetaka Shidara, Katsunari Shibata
- Journal Title
  
  Proc. of the 10th Int'l Symp. on Artificial Life and Robotics (AROB) (CD-ROM)
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Discretization of Series of Communication Signals in Noisy Environment by Reinforcement Learning2005
- Author(s)
  Katsunari Shibata
- Journal Title
  
  Adaptive and Natural Computing Algorithms (Ribeiro et al. (eds.))
  
  Pages: 486-489
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Growing Neural Network with Hidden Neurons2004
- Author(s)
  Ryusuke Kurino, Masanori Sugisaka, Katsunari Shibata
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 1
  
  Pages: 144-147
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Occurrence of state Confusion in the Learning of Communication Using Q-leaning2004
- Author(s)
  M.Nakanishi, M.Sugisaka, K.Shibata
- Journal Title
  
  Proc. of The 9th AROB (Infl Sympo. on Artificial Life and Robotics) Vol.2
  
  Pages: 663-666
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 報酬期待ニューロンの強化学習による発現モデル2004
- Author(s)
  石井慎也, 設楽宗孝, 柴田克成
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会2004講演論文集
  
  Pages: 63-68
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Occurrence of State Confusion in the Learning of Communication Using Q-leaning2004
- Author(s)
  Masanobu Nakanishi, Masanori Sugisaka, Katsunari Shibata
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 2
  
  Pages: 663-666
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 隠れニューロンの分離を伴う成長型ニューラルネットワーク2004
- Author(s)
  栗野竜輔, 柴田克成
- Journal Title
  
  電子情報通信学会技術研究報告 Vol. 103, No. 734
  
  Pages: 109-114
- NAID
  110003232597
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 視覚センサ付き実ロボットによる箱押し行動の獲得 -強化学習によるセンサーモータ間トータル機能獲得への第一歩-2004
- Author(s)
  柴田克成, 飯田大
- Journal Title
  
  第14回インテリジェント・システム・シンポジウム(FAN Symposium)講演論文集
  
  Pages: 123-128
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 強化学習とニューラルネットを用いた報酬期待ニューロンの発現モデル2004
- Author(s)
  石井慎也, 設楽宗孝, 柴田克成
- Journal Title
  
  第23回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 305-308
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 多入力ニューラルネットの学習過程における中間層ニューロン数の影響2004
- Author(s)
  藤田剛, 柴田克成
- Journal Title
  
  第23回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 369-372
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Growing Neural Network with Hidden Neurons2004
- Author(s)
  R.Kurinoz, M.Sugisaka, K.Shibata
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 1
  
  Pages: 144-147
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Q学習に基づく一方向コミュニケーションの創発における行動選択の影響2004
- Author(s)
  仲西賢展, 柴田克成
- Journal Title
  
  計測自動制御学会システム・情報部門学術講演会2004講演論文集
  
  Pages: 157-162
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] コミュニケーションの強化学習におけるノイズ付加による連続値信号の離散化2004
- Author(s)
  柴田克成
- Journal Title
  
  電子情報通信学会技術研究報告 Vol. 103, No. 734
  
  Pages: 55-60
- NAID
  110003232588
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Discretization of Analog Communication Signals by Noise Addition in Communication Learning2004
- Author(s)
  K.Shibata, M.Nakanishi
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 2
  
  Pages: 351-354
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Learning of Reaching a Colored Object Based on Direct-Vision-Based Reinforcement Learning and Acquired Internal Representation2004
- Author(s)
  K.Yuki, M.Sugisaka, K.Shibata
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 2
  
  Pages: 486-489
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Dynamics of a Recurrent Neural Network Acquired through the Learning of a Context-based Attention Task2004
- Author(s)
  Katsunari Shibata, Masanori Sugisaka
- Journal Title
  
  Artificial Life and Robotics Vol. 7
  
  Pages: 145-150
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Discretization of Analog Communication Signals by Noise Addition in Communication Learning2004
- Author(s)
  Katsunari Shibata, Masanobu Nakanishi
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 2
  
  Pages: 351-354
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Learning of Reaching a Colored Object Based on Direct-Vision-Based Reinforcement Learning and Acquired Internal Representation2004
- Author(s)
  Kazuyoshi Yuki, Masanori Sugisaka, Katsunari Shibata
- Journal Title
  
  Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics) Vol. 2
  
  Pages: 486-489
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Dynamics of a Recurrent Neural Network Acquired through the Learning of a Context based Attention Task2004
- Author(s)
  Katsunari Shibata, Masanori Sugisaka
- Journal Title
  
  Artificial Life and Robotics Vol.7
  
  Pages: 145-150
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] リカレントネットを用いた強化学習によるロボットの記憶に基づいた行動の学習2004
- Author(s)
  幸和芳, 柴田克成
- Journal Title
  
  第23回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 37-40
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 多入力ニューラルネットの学習過程における中間層ニューロン数の影響2004
- Author(s)
  幸和芳, 柴田克成
- Journal Title
  
  第23回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 369-372
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] 強化学習に基づくコミュニケーションの発現と伝達情報の解析2003
- Author(s)
  仲西賢展, 杉坂政典, 柴田克成
- Journal Title
  
  Proc. of SICE Annual Conf. 2003
  
  Pages: 71-74
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Acquisition of Box Pushing by Direct-Vision-Based Reinforcement Learning2003
- Author(s)
  Katsunari Shibata, Masaru Iida
- Journal Title
  
  Proc. of SICE Annual Conf. 2003 (CD-ROM)
  
  Pages: 1378-1383
- NAID
  130005440403
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Acquisition of Box Pushing by Direct-Vision-Based Reinforcement Learning2003
- Author(s)
  Katsunari Shibata Masaru Iida
- Journal Title
  
  Proc. of SICE Annual Conf. 2003 0324(pdf)
  
  Pages: 1378-1383
- NAID
  130005440403
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Growing Neural Network for Acquisition of 2-layer structure2003
- Author(s)
  R.Kurino, M.Sugisaka, K.Shibata
- Journal Title
  
  Proc. of IJCNN (Int'l Conf. on Neural Networks) (CD-ROM)
  
  Pages: 2512-2517
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Direct-Vision-Based強化学習によるカラー物体到達の学習と内部表現2003
- Author(s)
  幸和芳, 杉坂政典, 柴田克成
- Journal Title
  
  第22回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 65-68
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] メモリQ学習 -強化学習による選択的記憶の獲得-2003
- Author(s)
  柴田克成, 宮本沢巳
- Journal Title
  
  第22回計測自動制御学会九州支部学術講演会予稿集
  
  Pages: 57-60
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Growing Neural Network for Acquisition of 2-layer Structure2003
- Author(s)
  Ryusuke Kurino, Masanori Sugisaka, Katsunari Shibata
- Journal Title
  
  Proc. of UCNN (Int'l Conf. on Neural Networks) 2003 1455-703(pdf)
  
  Pages: 2512-2517
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Journal Article] Adaptive Space Reconstruction on Hidden Layer and Knowledge Transfer based on Hidden-level Generalization in Layered Neural network
- Author(s)
  Katsunari Shibata, Koji Ito
- Journal Title
  
  Trans. of SICE Vol.43, No.1
  
  Pages: 54-63
- NAID
  10018479914
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15300064
[Presentation] 層構造リカレントネットにおける感度調整学習時の感度と最大リアプノフ指数の関係2021
- Author(s)
  江島拓哉, 徳丸侑輝, 柴田克成
- 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
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] 感度調整学習を用いたリザバネットの構築2020
- Author(s)
  吉岡晴海, 松木俊貴, 柴田克成
- Organizer
  第39回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] リカレントネットにおける感度調整学習時の感度とリアプノフ指数の関係2020
- Author(s)
  江島拓哉, 徳丸侑輝, 柴田克成
- Organizer
  第39回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] カオスニューラルネットを用いた記憶問題の学習における不応性導入の影響2020
- Author(s)
  黒崎耕平, 柴田克成
- Organizer
  第39回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] リカレントネット内の感度調整によって学習を行う強化学習2020
- Author(s)
  徳丸侑輝, 柴田克成
- Organizer
  第39回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] リカレントネットによる状態遷移タスクの教師あり学習におけるカオス性の影響2020
- Author(s)
  大石将人,松木俊貴, 柴田克成
- Organizer
  第39回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] Q-learning with exploration driven by internal dynamics in chaotic neural network2020
- Author(s)
  Toshitaka Matsuki and Katsunari Shibata
- Organizer
  Int'l Joint Conf. on Neural Networks (IJCNN) 2020
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-20K11993
[Presentation] リカレントネットにおける感度調整学習でのカオスダイナミクスの生成と維持2019
- Author(s)
  徳丸侑輝, 柴田克成
- Organizer
  第38回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] 多層ニューラルネットにおける勾配消失問題解決法としての感度調整学習2019
- Author(s)
  長谷部圭亮, 柴田克成
- Organizer
  第38回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットを用いた記憶タスクの強化学習におけるカオス性の影響2019
- Author(s)
  大石将人, 柴田克成
- Organizer
  第38回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] 多層リードアウトを持つリザバを用いた強化学習におけるネットワーク構造の検討2019
- Author(s)
  吉岡晴海, 松木俊貴, 柴田克成
- Organizer
  第38回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Learning Time Constant of Continuous-Time Neurons with Gradient Descent2018
- Author(s)
  Toshitaka Matsuki & Katsunari Shibata
- Organizer
  The 6th Int'l Conf. on Robot Intelligent Technology and Applications
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] End-to-End強化学習による知能創発と「思考」創発へ向けた新しい強化学習2018
- Author(s)
  柴田克成
- Organizer
  第62回システム制御情報学会研究発表講演会
- Invited
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] 勾配法による動的なニューロンモデルの時定数の学習2018
- Author(s)
  松木俊貴，柴田克成
- Organizer
  第37回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Chaos-based Reinforcement Learning when Introducing Refractoriness in Each Neuron2018
- Author(s)
  Katsuki Sato & Katsunari Shibata
- Organizer
  The 6th Int'l Conf. on Robot Intelligent Technology and Applications
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスベース強化学習への誤差逆伝播法の適用2018
- Author(s)
  佐藤克樹，柴田克成
- Organizer
  第37回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Emergence of Intelligence through End-to-End Reinforcement Learning and Chaos-based Reinforcement Learning towards the Emergence of "Thinking"2017
- Author(s)
  Katsunari Shibata
- Organizer
  OIST(Okinawa Institute of Science and Technology ) Seminar
- Invited
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] New Reinforcement Learning Using a Chaotic Neural Network for Emergence of “Thinking”2017
- Author(s)
  Katsunari Shibata
- Organizer
  The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Influence of the Chaotic Property on Reinforcement Learning Using a Chaotic Neural Network2017
- Author(s)
  Yuki Goto, Katsunari Shibata
- Organizer
  Int'l Conf. on Neural Information Processing (ICONIP)2017
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Reinforcement Learning of a Memory Task using an Echo State Network with Multi-Layer Readout2017
- Author(s)
  Toshitaka Matsuki, Katsunari Shibata
- Organizer
  The Fifth Int'l Conf. on Robot Intelligence Technology and Applications
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] ニューラルネットワークを使った強化学習による行動学習を通した音声認識機能の創発2017
- Author(s)
  江越正大, 柴田克成
- Organizer
  第36回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットを用いた強化学習における不応性を有するカオスニューロンの導入2017
- Author(s)
  佐藤克樹, 後藤祐樹, 柴田克成
- Organizer
  第36回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Functions that Emerge through End-to-end Reinforcement Learning - The Direction for Artificial General Intelligence -2017
- Author(s)
  Katsunari Shibata
- Organizer
  The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Communications that Emerge through Reinforcement Learning Using a (Recurrent) Neural Network2017
- Author(s)
  Katsunari Shibata
- Organizer
  The 3rd Multidiscipliary Conf. on Reinforcement Learning and Decision Making (RLDM)17
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットを用いた強化学習におけるカオス性の影響2017
- Author(s)
  後藤祐樹, 柴田克成
- Organizer
  第36回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットの内部ダイナミクスを利用した記憶タスクの報酬に基づく学習2017
- Author(s)
  松木俊貴, 柴田克成
- Organizer
  第36回計測自動制御学会九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] BPWT を用いたリカレントネットの教師あり学習における相互結合部の重み値の影響2016
- Author(s)
  山本一真，柴田克成
- Organizer
  第32回計測自動制御学会九州支部学術講演会
- Place of Presentation
  佐賀大学（佐賀県佐賀市）
- Year and Date
  2016-11-26
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットを用いた強化学習における高次探索の創発2016
- Author(s)
  後藤祐樹，柴田克成
- Organizer
  第32回計測自動制御学会九州支部学術講演会
- Place of Presentation
  佐賀大学（佐賀県佐賀市）
- Year and Date
  2016-11-26
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] カオスニューラルネットの内部ダイナミクスを利用した記憶タスクの報酬に基づく学習2016
- Author(s)
  松木俊貴，柴田克成
- Organizer
  第32回計測自動制御学会九州支部学術講演会
- Place of Presentation
  佐賀大学（佐賀県佐賀市）
- Year and Date
  2016-11-26
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network2016
- Author(s)
  Toshitaka Matsuki and Katsunari Shibata
- Organizer
  Int'l Conf. on Neural Information Processing (ICONIP) 2016
- Place of Presentation
  Kyoto University (Kyoto, Japan)
- Year and Date
  2016-10-16
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Emergence of Higher Exploration in Reinforcement Learning Using a Chaotic Neural Network2016
- Author(s)
  Yuki Goto and Katsunari Shibata
- Organizer
  Int'l Conf. on Neural Information Processing (ICONIP) 2016
- Place of Presentation
  Kyoto University (Kyoto, Japan)
- Year and Date
  2016-10-16
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] Reinforcement Learning with Internal-Dynamics-based Exploration Using a Chaotic Neural Network2015
- Author(s)
  Katsunari Shibata and Yuta Sakashita
- Organizer
  Int'l Joint Conf. on Neural Networks (IJCNN) 2015
- Place of Presentation
  Killarney Convention Center (Ireland, Killarney)
- Year and Date
  2015-07-13
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] 動的ニューロンモデルを用いたニューラルネットへの因果トレースの適用2015
- Author(s)
  山本一真，柴田克成
- Organizer
  第２５回インテリジェント・システム・シンポジウム (FAN2015)
- Place of Presentation
  東北大学 (宮城県，仙台市)
- Year and Date
  2015-09-25
- Data Source
  KAKENHI-PROJECT-15K00360
[Presentation] 因果トレース - 並列かつ主観的時間スケールの導入による過去の処理の効率的学習 -2014
- Author(s)
  柴田克成
- 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
- Place of Presentation
  玉川大学，東京都
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] 因果トレース - 並列かつ主観的時間スケールの導入による過去の処理の効率的学習2014
- Author(s)
  柴田克成
- 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
- Place of Presentation
  東京
- Year and Date
  2014-03-18
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] RNNを用いた強化学習によるセンサ信号の時間変化を表すコミュニケーションの創発2013
- Author(s)
  朱祺, 柴田克成
- Organizer
  第32回計測自動制御学会九州支部学術講演会
- Place of Presentation
  長崎大学，長崎県
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] ニューラルネットを用いた強化学習による行動の学習を通した色恒常性の創発2013
- Author(s)
  ○柴田克成, 栗崎俊介
- 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
- Place of Presentation
  東京都町田市
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] 強化学習によるリカレントニューラルネットワーク内部での振動子創発の可能性2013
- Author(s)
  品矢裕介, 柴田克成
- Organizer
  第32回計測自動制御学会九州支部学術講演会
- Place of Presentation
  長崎大学，長崎県
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] 予測を要して連続動作を含む柔軟な行動のActor-Q学習による獲得2013
- Author(s)
  柴田克成, 後藤健太
- Organizer
  第23回インテリジェント・システム・シンポジウム (FAN 2013)
- Place of Presentation
  九州大学，福岡県
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] Emergence of Flexible Prediction-Based Discrete Decision Making and Continuous Motion Generation through Actor-Q-Learning2013
- Author(s)
  Katsunari Shibata and Kenta Goto
- Organizer
  Int'l Conf. on Development and Learning and on Epigenetic Robotics (ICDL-Epirob) 2013
- Place of Presentation
  Osaka, Japan
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] Emergence of Multi-Step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network2012
- Author(s)
  ○Mohamad Faizal bin Samsudin, Yoshito Sawatsubashi and Katsunari Shibata
- Organizer
  ICONIP (Int'l Conf. on Neural Information Processing Systems) 2012
- Place of Presentation
  Doha (Qatar)
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] ニューラルネットを用いた価値関数の学習における微分型トレースの提案2012
- Author(s)
  ○榎修志, 柴田克成
- Organizer
  計測自動制御学会システム・情報部門学術講演会
- Place of Presentation
  名古屋市
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] Emergence of Discrete and Abstract State Representation in Continuous Input Task through Reinforcement Learning2012
- Author(s)
  ○Yoshito Sawatsubashi, Mohamad Faizal bin Samsudin and Katsunari Shibata
- Organizer
  RiTA (Robot Intelligent Technology and Applications) 2012
- Place of Presentation
  光州（韓国）
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] リカレントネットを用いた強化学習における離散的かつ抽象的な状態表現の創発2012
- Author(s)
  ○沢津橋由人, Mohamad Faizal Bin Samusudin, 柴田克成
- Organizer
  計測自動制御学会システム・情報部門学術講演会
- Place of Presentation
  名古屋市
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] Emergence of Color Constancy Illusion through Reinforcement Learning with a Neural Network2012
- Author(s)
  ○Katsunari Shibata and Shunsuke Kurizaki
- Organizer
  Proc. of ICDL-EpiRob (Int'l Conf. on Development and Learning - Epigenetic Robotics) 2012
- Place of Presentation
  San Diego (USA)
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] 強化学習による合目的的かつ接地した一方向コミュニケーションの創発2012
- Author(s)
  ○柴田克成, 笹原冬月
- Organizer
  計測自動制御学会システム・情報部門学術講演会
- Place of Presentation
  名古屋市
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] Differential Trace in Learning of Value Function with a Neural Network2012
- Author(s)
  Katsunari Shibata and ○Shuji Enoki
- Organizer
  RiTA (Robot Intelligent Technology and Applications) 2012
- Place of Presentation
  光州（韓国）
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] あめとむちで知能を作る？　ー知能ロボットって...2011
- Author(s)
  柴田克成
- Organizer
  SOFT九州支部夏季ワークショップ2011(招待講演)
- Place of Presentation
  熊本県玉名市
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] あめとむちで知能を作る? -知能ロボットって本当に賢いの?2011
- Author(s)
  柴田克成
- Organizer
  SOFT九州支部夏季ワークショップ
- Place of Presentation
  玉名(熊本県)
- Year and Date
  2011-09-01
- Invited
- Data Source
  KAKENHI-PROJECT-23500245
[Presentation] 強化学習によるパターンの意味付けと記憶に基づく行動の獲得2010
- Author(s)
  柴田克成, 沢津橋由人, 宇都宮浩樹
- Organizer
  計測自動制御学会九州支部学術講演会
- Place of Presentation
  宮崎大学
- Year and Date
  2010-12-05
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] 可動カメラを用いたActor-Q学習による能動認識の学習2010
- Author(s)
  Armad Afif bin Mohd Faudi, 柴田克成
- Organizer
  SICE九州支部学術講演会
- Place of Presentation
  宮崎大学
- Year and Date
  2010-12-05
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] 強化学習によるパターンの意味付けと記憶に基づく行動の獲得2010
- Author(s)
  柴田克成, 沢津橋由人, 宇都宮浩樹
- Organizer
  SICE九州支部学術講演会
- Place of Presentation
  宮崎大学
- Year and Date
  2010-12-05
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] 可動カメラを用いたActor-Q学習による能動認識の学習2010
- Author(s)
  Armad Afif bin Mohd Faudi, 柴田克成
- Organizer
  計測自動制御学会九州支部学術講演会
- Place of Presentation
  宮崎大学
- Year and Date
  2010-12-05
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] 強化学習とリカレントネットを用いた並列で柔軟な学習制御システムの枠組み2010
- Author(s)
  高津聡志, 柴田克成
- Organizer
  SICE九州支部学術講演会
- Place of Presentation
  宮崎大学
- Year and Date
  2010-12-04
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] ニューラルネットを用いた強化学習による空間情報の抽象化と知識継承2009
- Author(s)
  柴田克成
- Organizer
  SICE九州支部学術講演会
- Place of Presentation
  九州大学伊都キャンパス
- Year and Date
  2009-11-29
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] リカレントニューラルネットを用いた強化学習による予測機能の創発2009
- Author(s)
  後藤健太, 松本康生, 柴田克成
- Organizer
  SICE九州支部学術講演会
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] ニューラルネットと強化学習を用いた音声によるコミュニケーションの自律学習2009
- Author(s)
  笹原冬月, 柴田克成
- Organizer
  SICE九州支部学術講演会
- Place of Presentation
  九州大学伊都キャンパス
- Year and Date
  2009-11-29
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] Contextual Behaviors and Internal Representations Acquired by Reinforcement Leaming with a Recurrent Neural Network in a Continuous State and Action Space Task2008
- Author(s)
  Hiroki, Utsunomiya, Katsunari Shibata
- Organizer
  Int'l Conf. 0n Neural Information Processing System (ICONIP)08
- Place of Presentation
  Auckland, New Zealand
- Year and Date
  2008-11-27
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] Improvement of Practical Recurrent Learning Method and Application into a Patt em Classification Task2008
- Author(s)
  Mohamad Faizal Samsudin, Katsunari Shibata
- Organizer
  Int'l Conf. on Neural Information Processing System (ICONIP)08
- Place of Presentation
  Auckland, New Zealand
- Year and Date
  2008-11-27
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] Learning of Action Generation from Raw Camera Images in a Real-World-like Environment by Simple Coupling of Reinforcement Learning and a Neural Network2008
- Author(s)
  Katsunari Shibata, Tomohiko Kawano
- Organizer
  Int'l Conf. on Neural Information Processing System (ICONIP)08
- Place of Presentation
  Auckland, New Zealand
- Year and Date
  2008-11-26
- Data Source
  KAKENHI-PROJECT-19300070
[Presentation] リカレントネットを用いた強化学習による記憶を利用した探索行動の学習2008
- Author(s)
  後藤健太, 柴田克成
- Organizer
  電気関係学会九州支部連合大会
- Data Source
  KAKENHI-PROJECT-19300070

1. OKABE Yoichi (50011169)

# of Collaborated Projects: 6 results

# of Collaborated Products: 0 results
2. KITAGAWA Manabu (30110711)

# of Collaborated Projects: 6 results

# of Collaborated Products: 0 results
3. HIROSE Akira (70199115)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
4. ITO Koji (30023310)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
5. MATSUNO Fumitoshi (00190489)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
6. KONDO Toshiyuki (60323820)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results

SHIBATA Katsunari 柴田 克成

柴田 克成 シバタ カツナリ

Research Projects

Research Products

Co-Researchers

Establishment of Chaos-based Dynamic Reinforcement Learning as Taking an Essential Technology to Realize Emergence of Thinking in AdvancePrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

From "Exploration" To "Thinking" - Development of Chaos Dynamics through Reinforcement LearningPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Exploration of a Breakthrough Technology for Emergence of Symbol Processing by Neuro-based Reinforcement Learning Considering Time AxisPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

A challenge towards how far the emergence of higher functions can be explained by reinforcement learning using a neural networkPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Autonomous, Harmonious and Purposive Acquisition of Various Functions of Robots by Reinforcement Learning and the Relation to the Intelligence FormationPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Study on Body Dynamics Formation and Pattern Generation for Motor/Action Learning

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

実ロボットによるDirect-Vision-Based強化学習の検証Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

センサ信号統合化学習と強化学習の融合に関する研究Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Institution

時間的情報を考慮したニューラルネットモデルの学習に関する基礎的研究

Principal Investigator

Project Period (FY)

Research Category

Research Institution

Coherent neural networks : Construction of prototypal subsystems

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

パルス型ニューロデバイスのためのニューラルネットモデルに関する基礎的研究

Principal Investigator

Project Period (FY)

Research Category

Research Institution

評価と動作の並列学習により障害回避を自己形成する自律能動学習機械の研究Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Fabrication of High-Tc Superconducting Co-planar Josephson Junctions Using Focused Ion Beam

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

SHIBATA Katsunari 柴田克成

柴田克成シバタカツナリ

[Book] 「ロボット情報学ハンドブック」(第7.5節ニューラルネットワークのみ)2010