研究業績 :

１．著書（共著）

  1. Construction and Application of Learning Petri Net. In Petri Nets
    (ed. Pawel Pawlewski),  pp. IN-TECH,  2012 (accepted)
    L.-B. Feng , M. Obayashi,     T. Kuremoto,K. Kobayashi

  2. A Chaotic Memory System Accelerated by an Emotional Model. In Amygdala: Structure, Functions and Disorders,
    (ed. Deniz Yilmazer-Hanke), pp., Nova Scientific Publishers, 2012 (accepted)
    T. Kuremoto,     M. Obayashi, K. Kobayashi
    .
  3. Instruction Learning Systems for Partner Robots, In Discrete Event Robots, (ed. Calin Ciufudean),pp., iConcept Press, 2012 (in press)
    T. Kuremoto,     M. Obayashi, K. Kobayashi

  4. A Robust  Reinforcement Learning System Using Concept of Sliding Mode Control for Unknown Nonlinear Dynamical System
    In Robust Control, Theory and Applications, 978-953-307-229-6, Chapter 9, pp.197-214, IN-TECH, 2011
    M. Obayashi, N. Nakahara, K. Yamada, T. Kuremoto, K. Kobayashi and L. Feng

  5. A Reinforcement Learning System Embedded Agent with Neural Network-Based Adaptive Herarchical Memory Structure
    In Advances in Reinforcement Learning, 978-953-307-369-9, Chapter 11 , pp.189-208, IN-TECH , 2011
    M. Obayashi, K. Narita, Y. Okamoto, T. Kuremoto, K. Kobayashi and L. Feng

  6. Objective-based Reinforcement Learning System for Cooperative Behavior Acquisition
    In Application of  Machine Learning, Chapter 14 , pp. 233-244, IN-TECH ,2010
    K. Kobayashi, M. Obayashi, T. Kuremoto

  7. Neural Forecasting Systems.
    In Reinforcement Learning, Theory and Applications (ed. Cornelius Weber, Mark Elshaw and Norbert Michael Mayer), Chapter 1, pp.1-20, IN-TECH , 2008
    T. Kuremoto, M. Obayashi, K. Kobayashi

  8. A Hippocampus-Neocortex Model for Chaotic Association
    In Trends in Neural Computation (Studies in Computational Intelligence) (ed. Ke Chen and Lipo Wang), Vol.35, Chapter 5, pp.111-133, Springer, 2006
    T. Kuremoto, T. Eto, K. Kobayashi and M. Obayashi


２．学術雑誌論文 (English)



  1. Handwriting Character Classification Using Freeman's Olfactory KIII Model,
    Artificial Life and Robotics    , Vol. No., pp., 2012 (Accepted)
    M. Obayashi, S. Koga, L.-B. Feng, T. Kuremoto, K. Kobayashi,

  2. H∞追従性能補償器を備えたリアルタイム強化学習制御システム，
    電気学会論文誌 Ｃ，Vol.132, No.6, pp. , 2012 (印刷中)
    内山祥吾， 大林正直，呉本尭，小林邦和

  3. A Gesture Recognition System with Retina-V1 Model and One-Pass Dynamic Programming.
    Neurocomputing, Vol. , No. , pp. , 2012 (Accepted)Kuremoto,
    T., Kinoshita, Y., Feng, L., Watanabe, S., Kobayashi, K., Obayashi M.:
  4. A Learning Petri Net,
    IEEJ Transactions on EEE, Vol.7, No.2, pp. 2012 (in press)
    Feng, L.-B., Obayashi M., Kuremoto, T., Kobayashi K.

  5. An Improved Internal Model of Autonomous Robots by a Psychological Approach.
    Cognitive Computation, Vol.3., No.4., pp.501-509,Springer, 2011
    Kuremoto,T., Obayashi, M., Kobayasahi, K., Feng, L.B.,
  6. 強化学習制御と適応H∞制御の協働型制御方式，
    電気学会論文誌Ｃ，Vol.131, No.8, pp.1467-1474, 2011
    大林正直，内山祥吾，呉本尭，小林邦和

  7. 相互結合型ネットワークにおけるメタヒューリスティクスを用いた動的想起，
    電気学会論文誌Ｃ，Vol.131, No.8, pp.1475-1484, 2011
    呉本尭，渡邊駿，小林邦和，馮 良炳，大林正直

  8. 部分的未知構造を持つ非線形システムのためのロバスト強化学習制御系設計法
    電気学会論文誌Ｃ，Vol.130,No.11, pp.2090-2011, 2010
    中野一宏，大林正直，呉本尭，小林邦和　
  9. 間接型適応的自己構造ファジィニューラルネットワーク制御システム
    電気学会論文誌Ｃ，Vol.130, No.10, pp.1882-1887, 2010
    牧野吉宏，大林正直，呉本尭，小林邦和
  10. Intelligent agent construction using the attentive characteristic patterns of chaotic neural networks.
    Artifical Life and Robotics,Vol.15, No.2, pp.216-220, 2010
    M . Obayashi, Liang-Bing Feng , T. Kuremoto and K. Kobayashi
  11. Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System(PDF),
    Journal of Robotics, ,Vol.2010,pp.1-9,2010 (in press)
    T. Kuremoto, T. Komoto, K. Kobayashi, , and M. Obayashi
  12. An Improved Internal Model for Swarm Formation and Adaptive Swarm Behavior Acquisition
    Journal of Circuits, Systems, and Computers, Vol.18, No.8, pp.1517-1531, 2009
    T. Kuremoto, Y. Yamano, M. Obayashi, and K. Kobayashi
  13. Adaptive Swarm Behavior Acquisition by a Neuro-Fuzzy System and Reinforcement Learning Algorithm,
    International Journal of Intelligent Computing and Cybernetic, Vol.2, No.4, pp.724-744, 2009.
    T. Kuremoto, M. Obayashi, and K. Kobayashi,

  14. TD誤差に基づく強化学習のメタパラメータ学習法
    電気学会論文誌Ｃ，Vol.129, No.9, pp.1730-1736, 2009
    溝上裕之，小林邦和，呉本尭，大林正直
  15. 局所線形モデルを導入したウェーブレットニューラルネットワークのベイズ的設計法
    電気学会論文誌C，Vol.129, No.7, pp.1356-1362, 2009
    小林邦和，呉本尭，大林正直
  16. A Dynami Associative Memory System by Adopting Amygdala Model
    Artificial Life and Robotics, Vol. 13. No. 2, pp.478-482, 2009
    T. Kuremoto, T. Ohta, K. Kobayashi, M. Obayashi
  17. A Robust Reinforcement Learning Using Concept of Slide Mode Control,
    Artificial Life and Robotics, Vol. 13, No. 2,  pp.526-530, 2009
    M. Obayashi, N. Nakahara, T. Kuremoto, K. Kobayashi
  18. A Reinforcement Learning Method Based on Immune Network Adapted to Semi Markov Decision Process
    Artificial Life and Robotics, Vol. 13, No. 2, pp.538-542, 2009
    N. Kogawa, M. Obayashi, K. Kobayashi, T. Kuremoto
  19. 一時的滞留機能を持つ過渡的カオス連想記憶モデル
    電気学会論文誌Ｃ，Vol.128, No.12, pp.1852-1858, 2008
    大林正直，成田顕一郎，小林邦和，呉本尭
  20. 状態予測型強化学習システム
    電気学会論文誌Ｃ，Vol.128, No.8, pp.1303-1311, 2008
    小林邦和，中野浩二，呉本尭，大林正直
  21. Transient-SOM を用いた手画像命令学習システム
    計測自動制御学会論文集，Vol.43, No.11, pp.1004-1006, 2007
    羽野ともえ，呉本尭，小林邦和，大林正直
  22. 免疫回路網式強化学習
    計測自動制御学会論文集，Vol.43, No.6, pp.525-527, 2007
    小川長久，大林正直，小林邦和，呉本尭
  23. カオスニューラルネットワーク連想記憶モデルにおける活性化関数の形状とその評価
    電気学会論文誌Ｃ， Vol.126, No. 11, pp. 1401-1405, 2006
    大林正直，大宮理恵，呉本尭，小林邦和
  24. 時変パラメータを持つ進化的強化学習システム，
    電気学会論文誌，124-(C)，1478-1483，(2004)
    梅迫公輔，大林正直，小林邦和
  25. 自己組織化型ファジィ強化学習システム,
    計測自動制御学会論文集, 39(7), 699-701, (2003)
    梅迫公輔，大林正直，小林邦和
  26. 関数型記憶行列を持つカオスニューラルネット連想記憶システムと相互情報量,
    電気学会論文誌, 123-C(9), 1631-1637,(2003)
    大林正直, 夕田憲治, 大宮理恵, 小林邦和
  27. カオスの縁を考慮したカオスシステムのニューラルネットワーク制御
    計測自動制御学会論文集，Vol.38,No.10,pp.907-914，(2002)
    大林正直，梅迫公輔，中山大輔

  28. 関数型結合重みを持つニューラルネットワークを用いた学習の高速化とその非線形制御への応用，
    電気学会論文誌， Vol.121-C,No.2, (2001)
    大林正直，梅迫公輔，小林邦和

  29. Radial Basis Function を用いたカオスニューラルネット ワークとそのメモリサーチへの応用，
    電気学会論文誌，Vol.120-C,No.10, (2000)
    大林正直，渡辺賢治，小林邦和

  30. Learning Petri Networks and Its Application to Non-linear System Control,
    IEEE Transactions on Systems,Man,and Cybernetics, Part B:Cybernetics,
    Vol.28,No.6,781-789 (December 1998)
    K.Hirasawa,M.Ohbayashi,S.Sakai and J.Hu
     
  31. Chaos Universal Learning Network Clustering Control,
    Journal of Robotics and Mechatronics,Vol.10,No4,305-310 (1998)
    K.Hirasawa,J.Misawa,J.Hu,J.Murata,M.Ohbayashi and Y.Eki

  32. ファジィ評価と２次微分を考慮した一般化学習ネットワー クによるロバスト制御方式，
    計測自動制御学会論文集，Vol.34,No.9,1246-1254 (1998)
    大林正直，平澤宏太郎，利光克之，他２名

  33. 一般化学習ネットワークの２次微分を用いた非線形ダイナミカルシステムの抑制／活性化制御
    計測と制御，Vol.37,No.8,586-600 (1998)
    大林正直，平澤宏太郎，橋本雅之

  34. Computing Higher Order Derivatives in Universal Learning Networks,
    Journal of Advanced Computatinal Intelligence,Vol.2,No2,47-53 (1998)
    平澤宏太郎，胡敬炉，大林正直，村田純一

  35. ニューラルネットワークの適応的ランダム探索最適化手法 - RasID-
    計測自動制御学会論文集，Vol.34,No.8,1088-1096 (1998)
    平澤宏太郎，東郷和幸，胡敬炉，大林正直，他２名

  36. 機能局在型学習ネットワーク（Learning Petri Network） の非線形制御への応用,
    電気学会論文誌，Vol.118-C,No.6,873-881 (1998)
    大林正直，平澤宏太郎，堺慎悟，胡敬炉

  37. 確率分布・可能性分布を考慮したオートマトン学習ネット ワーク,
    電気学会論文誌，Vol.118-D,No.3,291-299 (1998)
    平澤宏太郎，原田昌幸，大林正直，他２名

  38. 一般化学習ネットワークの２次微分を用いた非線形ダイナミカルシステムの外部入力変動に対するロバスト制御方式
    電気学会論文誌，Vol.118-D,No.3,300-307 (1998)
    大林正直，平澤宏太郎

  39. 確率一般化学習ネットワーク理論,
    電気学会論文誌，Vol.118-C,No.2,224-231 (1998)
    平澤宏太郎，大林正直，村田純一，胡敬炉

  40. ニューラルネットワークの学習におけるB.P.M.と L.S.M.の最適評価指標探索能力の比較評価
    計測自動制御学会論文集，Vol.34,No.1,41-47 (1998)
    古賀勝，平澤宏太郎，大林正直

  41. Universal Learning Network-Based Fuzzy System andIts Application to Non-Linear Control System,
    計測自動制御学会論文集，Vol.33, No9,1259-1266 (1997)
    大林正直，平澤宏太郎，呉 端，Ning Shao

  42. Modeling Nonlinear Dynamic Systems Using Universal Learning Network with Filtering Mechanism,
    電気学会論文誌，Vol.117-C,No.9,1259-1266 (1997)
    韓 敏，平澤宏太郎，大林正直，藤田寛之

  43. オートマトン学習ネットワーク理論,
    電気学会論文誌，Vol.117-C,No.8,1069-1075 (1997)
    池内光雄，平澤宏太郎，大林正直

  44. Robust Control for System Parameter PerturbationUsing Second Order Derivatives of Universal Learning Network,
    計測自動制御学会論文集，Vol.33,No4,289-295 (1997)
    大林正直，平澤宏太郎，橋本雅之，村田純一

  45. 一般化学習ネットワークの２次微分を用いた非線形ダイナミカルシステムの初期値変動に対するロバスト制御方式,
    電気学会論文誌，Vol.117-D,No.3,289-297 (1997) 
    大林正直，平澤宏太郎

  46. 一般化学習ネットワークによるホロニック制御,
    電気学会論文誌，Vol.117-D,No.3,281-288 (1997)
    楠見尚弘，平澤宏太郎，大林正直

  47. ファジィ重み係数多目的非線形制御システムの一般化学習ネットワークによる構成,
    電気学会論文誌，Vol.117-D,No.3,298-305 (1997)
    平澤宏太郎，大林正直，山本祐督

  48. 多重ブランチをもつ一般化学習ネットワークにおけるカオス制御,
    電気学会論文誌，Vol.117-C,No.3,262-271 (1997)
    古賀勝，平澤宏太郎，大林正直

  49. 一般化学習ネットワークの安定性理論,
    電気学会論文誌，Vol.116-C,No.8,973-981 (1996)
    平澤宏太郎，大林正直，古賀勝

  50. 微分情報を用いたランダム探索最適化手法-Likelihood Search Method (L.S.M.)
    計測自動制御学会論文集，Vol.32,No8,1277-1286 (1996)
    古賀勝，平澤宏太郎，大林正直，村田純一

  51. 一般化学習ネットワーク理論,
    電気学会論文誌，Vol.116-C,No.7,794-804 (1996)
    平澤宏太郎，大林正直，藤田寛之，古賀勝

  52. 一般化学習ネットワークにおけるカオス制御方式,
    計測自動制御学会論文集，Vol.32,No6,844-853 (1996)
    古賀勝，平澤宏太郎，大林正直，村田純一

  53. フォワードプロパゲーション一般化学習ネットワーク理論,
    電気学会論文誌，Vol.116-C,No.6,692-698 (1996)
    平澤宏太郎，大林正直，古賀勝

  54. ペトリネットに準拠した機能局在型学習ネットワーク- Learning Petri Network - ，
    計測自動制御学会論文集，Vol.32,No2,241-250 (1996)
    平澤宏太郎，岡誠司，大林正直，他２名

  55. 一般化学習ネットワークの高次微分の計算理論,
    電気学会論文誌，Vol.115-C,No.12,1499-1506 (1996)
    平澤宏太郎，大林正直，古賀勝，他２名

  56. パラメータ変動を伴うシステムのロバスト極配置制御とその非線形システムへの応用,
    電気学会論文誌，Vol.115-C,No.8,984-991 (1995)
    大林正直，平澤宏太郎，村田純一，他２名

  57. 脳の機能局在をペトリネットでモデル化する方式の提案,
    電気学会論文誌，Vol.115-C,No.5,719-727 (1995)
    平澤宏太郎，大林正直，村田純一，他４名

  58. 扇状領域極配置を満たすフィードバックゲインの決定法,
    電気学会論文誌，Vol.114-C,No.6,705-712 (1994)
    大林正直，相良節夫，平澤宏太郎，村田純一


もとに戻る


３．国際会議議事録

  1. Handwriting Character Classification Using Freeman's Olfactory Model,
    Proceedings of the 17th International Symposium on Artificial Life and Robotics (AROB2012), pp.714-717, Jan. 19-21, 2012 (Beppu, Japan)
    Obayashi, M., Koga, S, Kuremoto, T., Ko    bayashi, K.
  2. Development of a Brain Computer Interface Using Inexpensive Commercial EEG Sensor with One Channel,
    Proceedings of the 17 International Symposium on Artificial Life and Robotics (AROB2012    ), pp.1040-1043, Jan. 19-21, 2012 (Beppu, Japan)
    Obayashi, M., Watanabe, K.,Kuremoto, T., K    obayashi, K.
  3. A Neuro-Fuzzy Network with Reinforcement Learning Algorithm for Swarm Learning.
    Proceedings of 2011 International Conference on Future Wireless Networks and Information Systems, Lecture Note in Electronic Engineering, Springer, (ICFWI 2011), pp.,  Dec. 1-2. 1, 2011 (Macau, China)
    Kuremoto, T., Yamano, Y., Feng, L., Kobayashi, K., Obayashi M.

  4. Optimization and Verification for a Robot Control System on Leraning Petri Net Model,
    Proceedings of the 3rd     International Asia Conference on Informatics in Control, Automation, and Robotics (CAR 2011), Lecture Note in Electronic Engineering (LNEE), Vol. 133, pp.815-823,  Springer-Verlag, Dec. 24-25, 2011 (Shenzhen, China)
    Feng, L., Obayashi, Kuremoto, T., Kobayashi, K.

  5. H_infinity Robust Reinforcement Learning Control System with Auto-Structuring  Fuzzy Neural Network,
    Proceedings of the 3rd International Symposium on Digital Manufac    turing (ISDM 2011), pp., Nov. 30-Dec. 2, 2011 (Kitakyushu, Japan) (in press)
    Uchiyama, S., Obayashi, M., Kuremoto, T.,Kobay    ashi, K.
  6. An Action Selection Method Based on Estimation of Other's Intention in Time-Varying Multi-Agent Environments,
     Prodeedings of International Conference on Neural Information Proccessing (ICONIP 2011),Lecture Note in Computer Science (LNCS) Vol. 7064, pp.76-85,Springer-Verlag, Nov., 14-17, 2011 (Shanghai, China)
    Kobayashi, K., Kanehira, R., Kuremoto, T., Obayashi, M.

  7. Robust Reinforcement Learning Control System with H-infinity Tracking Performance Compensator,
    Proceedings of International Conference on Control, Automation, and Systems 2011 (ICCAS 2011), pp.248-253, Oct. 26-29, 2011 (Gyeonggi-do, Korea)
    Uchiyama,     S., Obayashi, M., Kuremoto, T., and Kobayashi, K.

  8. Intelligent Tracking Control Method of A Target by Group of Agents with Nonlinear Dynamics,
    Proceedings of International Conference on Control, Automation, andSystems 2011 (ICCAS 2011), pp.928-933, Oct. 26-29, 2011 (Gyeonggi-do, Korea)
    Obayashi, M., Yokoji, Y., Uchiyama, S., Feng, L-B., Kuremoto, T., and Kobayashi, K.
  9. A Gesture Recognition System Using One-Pass DP Method.
    ICIC 2011, Springer, Communications in Computer and Information Science, Vol., pp. Aug. 12-14, 2011 (Zhengzhou, China) (in press)
    KuKinoshita, Y., Feng, L., Watanabe, S., Kobayashi, K., Obayashi M.

  10. A Human-Machine Interaction System: A Voice Command Learning System Using PL-G-SOM,
    Proceedings of International Conference on  Industrial Engineering and Management Special Session Within Mass (IEEE-IEM 2011),  pp. Aug. 12-14, 2011 (Zhengzhou, China) (in press)
    Kuremoto, T., Yamane, T., Feng, L.-B., Kobayashi, K., Obayashi, M.
  11. A Reinforcement Learning System Embedded Agent with Neural Network-Based Multi-Valued Pattern Memory Structure,
    Proc. of International Conference on Control, Automation, and Systems 2010(ICCAS2010) ,pp.176-181,Oct. 27-30, 2010 (Gyeonggi-do,Korea)
    M. Obayashi, T. Nishida, T. Kuremoto, K. Kobayashi and L., Feng

  12. An Intelligent Control System Construction Using Hige-Level Time Petri Net and Reinforcement Learning,
    Proc. of International Conference on Control, Automation, and Systems 2010(ICCAS2010), ,,pp.535-539Oct. 27-30, 2010 (Gyeonggi-do,Korea)（in press）
    Feng L., M. Obayashi, T. Kuremoto, K. Kobayashi

  13. Autonomic Behaviors of Swarm Robots Driven by Emotion and Curiosity,
    Proc. of 2010 International Conference on Life System Modeling and Simulation & 2010 International Conference on Intelligent Computing for Sustainable Energy and Environment (LSMS & ICSEE 2010),Springer-Verlag, Lecture Notes in Artificial Intelligence Vol.6330, pp.541-547, Sep. 17-20, 2010 (Wuxi, China)
    T. Kuremoto, M. Obayashi , K. Kobayashi , Feng, L.
  14. Intelligent Agent Construction Using the Idea of the Attentive Characteristic Pattern in A Chaotic Neural Network,
    Proc. of the 15th International Symposium on Artificial Life and Robotics (AROB2010), pp.597-600, February 4-6, 2010 (Beppu, Japan)
    M. Obayashi., T. Kuremoto, K. Kobayashi
  15. A Learning Petri Net Model Based on Reinforcement Learning,
    Proc. of the 15th International Symposium on Artificial Life and Robotics (AROB2010), pp.290-293, February 4-6, 2010 (Beppu, Japan)
    Feng, L., M. Obayashi, T. Kuremoto, K. Kobayashi
  16. A Robust Reinforcement Learning System Using Sliding Mode Control with Variable Filters,
    Proc. of 2009  International Automatic Control Conference (CACS 2009), CD-ROM, Nov. 27-29, 2009 (Taipei, Taiwan)
    M. Obayashi, K. Yamada, T. Kuremoto, K. Kobayashi
  17. A Meta-learning Method Based on Temporal Difference Error, Lecture Notes in Computer Science, Vol.5863, pp.530-537, Springer-Verlag, 2009 ,
    Proc. of 16th International Conference on Neural Information Processing (ICONIP 2009), pp. 373-374, Dec. 1-5, 2009 (Bangkok, Thailand)
    K. Kobayashi ,H. Mizoue, T. Kuremoto, M. Obayashi
  18. A Functional Model of Limbic System of Brain,
    Proc. of 2009 International Conference on Brain Informatics (BI2009),Springer-Verlag, Lecture Notes in Artificial Intelligence Vol.5819, pp.135-146, October 22-24, 2009 (Beijing, China)
    T. Kuremoto, T. Ohta, K. Kobayashi, M. Obayashi
  19. A Voice Instruction Learning System Using PL-T-SOM,
    Proc. of the 2nd International Conference on Image and Signal Processing (CISP2009), pp.4294-4299 (IEEE eXpress Conference Publishing, ISBN: 978-1-4244-4130-3), October 17-19, 2009 (Tianjin, China)
    T. Kuremoto, T. Komoto, K. Kobayashi., M. Obayashi
  20. A Self-Organized Fuzzy-Neuro Reinforcement Learning System for Continuous State Space for Autonomous Robots
    Proc. of  International Conference on Computational Intelligence for Modelling, Control and Automation 2008 (CIMCA08), pp.552-559, 10-12 Dec. 2008 (Vienna, Austria)
    M. Obayashi, T. Kuremoto, K. Kobayashi:
  21. A Reinforcement Learning System with Chaotic Neural Neworks-Based Adaptive Herarchical Memory Structure for Autonomous Robots
    Proc. of International Conference on Control, Automation and Systems 2008 (ICCAS 2008), pp. 69-74, 2008 (Seoul, Korea)
    M. Obayashi, K. Narita, T. Kuremoto, K. Kobayashi
  22. A Neuro-Fuzzy Learning System for Adaptive Swarm BehaviorsDealing with Continuous State Space,
    Proc. of ICIC 2008, Springer-Verlag, Lecture Notes in Computer Science Vol.5227, pp.675-683, 2008 (Shanghai, China) (Abstract)
    T. Kuremoto , M. Obayashi , K. Kobayashi , H. Adachi , K. Yoneda
  23. A Reinforcement Learning System for Swarm Behaviors
    Proc. of IEEE World Congress on Computational Intelligence (WCCI 2008 / IJCNN 2008), pp.3710-3715,June 1st- June 7th, 2008 (Hong Kong)
    T. Kuremoto , M. Obayashi, K. Kobayashi., H. Adachi ,  K. Yoneda 
  24. Chaotic Dynamical Associative Memory Model Using Supervised Learning.
    Proc. of the 13th International Symposium on Artificial Life and Robotics (AROB2008), pp.555-558, January 31-February 2, 2008 (Beppu, Japan).
    M. Obayashi, Y. Yano , K. Kobayashi., T. Kuremoto　,
  25. A Dynamic Associative Memory System Adopting Amygdala Model.
    Proc. of the 13th International Symposium on Artificial Life and Robotics (AROB2008), pp.563-566, January 31-February 2, 2008 (Beppu, Japan).
    T. Kuremoto, T. Ohta, K. Kobayashi , M. Obayashi
  26. A Reinforcement Learning Method Based on Immune Network Adapted to Semi Markov Decision Process.
    Proc. of the 13th International Symposium on Artificial Life and Robotics (AROB2008), pp.63-66, January 31-February 2, 2008 (Beppu, Japan).
    N. Kogawa , M. Obayashi., K. Kobayashi, T. Kuremoto,

  27. A Robust Reinforcement Learning Using Concept of Sliding Mode Control.
    Proc. of the 13th International Symposium on Artificial Life and Robotics (AROB2008), pp.547-550, January 31-February 2, 2008 (Beppu, Japan).
    M. Obayashi, N. Nakahara , T. Kuremoto, K. Kobayashi

  28. Cooperative Behavior Acquisition of Multiple Autonomous Mobile Robots by an Objective-based Reinforcement Learning System.
    Proc. of International Conference on Control, Automation and Systems (ICCAS2007), pp.777-780, October 17-20, 2007 (Seoul, Korea)
    K. Kobayashi, K. Nakano , T. Kuremoto , M. Obayashi
  29. Robot Feeling Formation Based on Image Features.
    Proc. of International Conference on Control, Automation and Systems (ICCAS2007), pp.758-761, October 17-20, 2007 (Seoul, Korea)
    T. Kuremoto, T. Hano , K. Kobayashi , M. Obayashi
  30. Forecasting Time Series by SOFNN with Reinforcement Learning.
    Proc. of the 27th Annual International Symposium on Forecasting (ISF2007), pp.99, June 24-27, 2007 (New York, USA)
    T. Kuremoto, M. Obayashi, K. Kobayashi
  31. Controller Design Based on Immune Concept and Its Application to Chaotic Control.
    Proc. of 2006  International Automatic Control Conference (CACS 2006). pp.327-331, 2006 (Tamsui, Taiwan)
    M. Obayashi, N. Kogawa , S. Toyota , K. Kobayashi , T. Kuremoto
  32. For Partner Robots: A Hand Instruction Learning System Using Transient-SOM.
    Proc. of the 2nd Interenational Conference on Natural Computation and The 3rd International Conference on Fuzzy Systems and Knowledge Discovery (ICNC '06-FSKD'06), pp.403-414, 2006 (Xi'an China)
    T. Kuremoto , T. Hano , K. Kobayashi , M. Obayashi
  33. Learning Method of Cooperative Team Play Using the Immune System.
    Proc. of the 11th International Symposium on Artificial Life and Robotics (AROB2006), pp.183-186, Jan.23 -25, 2005 (Beppu, Japan)
    N. Kogawa , M. Obayashi , A. Maeda , K. Kobayashi , T. Kuremoto

  34. A Reinforcement Learning System Based on State Space Construction Using Fuzzy ART.
    Proc. of SICE Annual Conference 2005 , pp.3653-3658, 2005 (Okayama, Japan)
    K. Kobayashi , S. Mizuno , T. Kuremoto , M. Obayashi
  35. A Multi-layered Chaotic Neural Network for Associative Memory.
    Proc. of SICE Annual Conference 2005, pp.1020-1023, 2005 (Okayama, Japan)
    T. Kuremoto , T. Eto , K. Kobayashi , M. Obayashi
  36. Nonlinear Prediction by Reinforcement Learning.
    Proc. of ICIC 2005 Springer-Verlag, Lecture Notes in Computer Science Vol.3644, pp.1085-1094, 2005 (Hefei, China)
    T. Kuremoto, K. Kobayashi., M. Obayashi
  37. A Chaotic Model of Hippocampus-Neocortex.
    Proc. of ICNC'05-FSKD'05 Springer-Verlag, Lecture Notes in Computer Science Vol.3610, pp.439-448, 2005 (Changsha, China)
    T. Kuremoto , T. Eto , K. Kobayashi , M. Obayashi
  38. Cooperative behavior acquisition for multiple autonomous mobile robots.
    Proc. of the 10th International Symposium on Artificial Life and Robotics (AROB2005), 543-546, February 4-6, 2005 (Beppu, Japan)
    K. Nakano , M. Obayashi., K. Kobayashi , T. Kuremoto

  39. Construction and strategy of a soccer team by the agent using immune concept.
    Proc. of the 10th International Symposium on Artificial Life and Robotics (AROB2005), 342-345, February 4-6, 2005 (Beppu, Japan)
    N. Kogawa, M. Obayashi., A. Maeda , K. Kobayashi , T. Kuremoto

  40. Computing Slow Optical Flow by Interpolated Quadratic Surface Matching.
    Proc. of the 4th IASTED International Conference on Visualization, Imaging, and Image Processing (VIIP2004), pp.346-351, September 6-8, 2004 (Marbella, Spain)
    T. Kuremoto , K. Koga , K. Kobayashi , M. Obayashi
  41. Predicting Chaotic Time Series by Reinforcement Learning.
    Proc. of the 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS2003), CD-ROM, December 15-18, 2003 (Singapore)
    T. Kuremoto , M. Obayashi , A. Yamamoto , K. Kobayashi
  42. Neural Prediction of Chaotic Time Series Using Stochastic Gradient Ascent Algorithm.
    Proc. of the 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (SSS03 ), pp.17-22, October 30-31, 2003 (Ube, Yamaguchi)
    T. Kuremoto , M. Obayashi , A. Yamamoto , K. Kobayashi
  43. Reinforcement Learning System with Time Varying Parameters Using Neural Network.
    Proc. of the 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (SSS03), pp.11-16 , October 30-31, 2003 (Ube, Yamaguchi)
    M. Obayashi , T. Oda , K. Kobayashi , T. Kuremoto, H. Kitano
  44. Actor-Critic Reinforcement Learning System Time-Varying Parameters.
    Proc. of 2003 International Conference on Control,Automation,and Systems (ICCAS2003), pp.138-141, October 22-25, 2003
    M. Obayashi, K. Umesako, T.Oda, K. Kunikazu, B. Y. Wu
  45. Computing Slow Optical Flow by Interpolated Quadratic Surface Matching,
    Proc. of the 4th IASTED International Conference on Visualization, Imaging, and Image Processing (VIIP2004), CD-ROM, 2004
    T. Kuremoto, K. Koga, K. Kobayashi, M. Obayashi,
  46. Evolutionary and time-varying reinforcement learning system based on Overlap of rules,
    Proc. of 6th Japan-France Congress on Mechatronics 4th Asia-Europe Congress on Mechatronics (JFM2003), 202-207, 2003
    K. Umesako, M. Obayashi, K. Kobayashi

  47. Reinforcement Learning System with Time Varying Parameters Using Neural Network,
    Proc. of the 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (SSS03), 1-6, 2003
    M. Obayashi, T. Oda, K. Kobayashi, T. Kuremoto,H. Kitano

  48. Neural Prediction of Chaotic Time Series Using Stochastic Gradient Ascent Algorithm.
    Proc. of the 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (SSS03), 1-6, 2003
    T. Kuremoto, M. Obayashi, A. Yamamoto, K. Kobayashi

  49. Predicting Chaotic Time Series by Reinforcement Learning,
    Proc. of the 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS2003), 1-6, 2003
    T. Kuremoto, M. Obayashi, A. Yamamoto, K. Kobayashi

  50. Actor-Critic Reinforcement Learning System with Time-Varying Parameters,
    Proc. of international Conference on Control, Automation, and Systems, (ICCAS2003), 138-241,2003 (Gyeongju, Korea)
    Obayashi M., Umesako K., Oda T., Kobayashi K.

  51. Evolutionary and time-varying reinforcement learning system for unobservable dynamic environment,
    Proc. of the Eighth International Symposium on Artificial Life and Robotics (AROB2003), pp.82-85, January 24-26, 2003 (Oita, Japan)
    Umesako, K., Obayashi, M. Kobayashi, K.,

  52. Chaotic System Control Considering Edge of Chaos Using Neural Network,
    Proc. of the Internatinal Conference on Control, Automation and Systems (ICCAS2002),
    Masanao Obayashi, Kousuke Umesako, Daisuke Nakamura

  53. Mobile Robot Control Using Self-organized Fuzzy Reinforcement Learning SYstem,
    Proc. of the Internatinal Symposium on Advanced Control of Industrial Process (AdCONIP2002),pp.513-519,2002
    Umesako K., Obayashi M., Kobayashi K.

  54. Fast Reinforcement Learning Using Asymmetric Probability Density Function,
    Proc. of 41st Society of instrument and Control Engineers,pp.907-912(SICE2002),
    Umesako, K., Obayashi, M. Kobayashi, K.

  55. Evolutionary Reinforcement Learning System with Time-varing Parameters,
    Proc. of the Internatinal Conference on Control, Automation and Systems (ICCAS2002), pp.1284-1287, October 16-19, 2002 (Jeonbuk, Korea)
    Umesako, K., Obayashi, M. Kobayashi, K.

  56. A Chaotic Memory Search Model Based on Associative Dynamics Using Features in Stored Patterns,
    Proc. of 41st Society of Instrument and Control Engineering Annual Conference (SICE2002), pp.2919-2924, August 5-7, 2002 (Osaka, Japan)
    Kobayashi, K., Watanabe, K. Obayashi, M.

  57. Memory Search Using Chaotic Neural Network with Feature Dynamics,
    Proc. of International Conference on Neural Information Processing,pp1124-1129,Nov.,2000
    K.Watanabe, M.Obayashi, K.Kobayashi

  58. Reinforcement Learning for Dynamics in Incomplete Observation Environment,
    Proc. of International Conference on Neural Information Processing,pp434-439,Nov.,2000
    K.Umesako, M. Obayashi, K.Kobayashi

  59. An Effective Solution to Large-scale Traveling Salesman Problems Using Chaotic Neural Networks,
    Proc. of International Conference on Neural Information Processing,pp459-464,Nov.,2000
    T.Nagashima, K.Kobayashi, M.Obayashi

  60. Evaluation of Three Types Input-Output Functions of Chaotic Neural Networks in Memory Search Problem,
    Proc. of International Conference on Neural Information Processing,pp1130-1135,Nov.,2000
    M.Obayashi, K.Yuda, K.Watanabe, K.Kobayashi

  61. A New Method for Faster Neural Networks Learning Introducing Functions of Synaptic Weights,
    Proc. of International Conference on Neural Information Processing,pp1178-1183,Nov.,1999
    M.Obayashi, K.Kobayashi

  62. Indirect Encoding Method with Variable Length Gene Code to Optimize Neural Network Structure,
    Proc. of IEEE International Joint Conference on Neural Networks,CD-ROM,May,1999
    K.Kobayashi, M.Obayashi

  63. Robust Control for Nonlinear Systems by Universal Learning Network Considering Fuzzy Criterionand Second Order Derivatives,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    M.Ohbayashi, K.Hirasawa, K.Toshimitsu,J.Murata,J.Hu

  64. A Computation Scheme for Higher Order Derivatives in Universal Learning Networks,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    J.Hu, K.Hirasawa,M.Ohbayashi,J.Murata

  65. Clustering Control of Chaos Universal Learning Network,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    K.Hirasawa,J.Misawa,M.Ohbayashi,J.Hu

  66. A New Random Search Method for Neural Network Learning,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    K.Hirasawa,J.Murata,M.Ohbayashi,J.Hu,M.Koga

  67. Adaptive Control of Nonlinear Black-Box Systems Based on Universal Learning Networks,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    J.Hu, K.Hirasawa,J.Murata,M.Ohbayashi

  68. Identification of Nonlinear Black-Box Systems on Universal Learning Networks,
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    J.Hu, K.Hirasawa,J.Murata,M.Ohbayashi

  69. A New Random Search Method for Neural Network Learning,
    - Random Search with Variable Search Length (RasVal) -
    Proc. of IEEE International Joint Conference on Neural Networks,May,1998
    K.Hirasawa,K.Togo,J.Murata,M.Ohbayashi,etal

  70. Holonic Control System Using Fuzzy Criterion,
    Proc. of Third International Symposium on Artificial LIfe and Robotics, Feb.,1998
    N.Kusumi,K.Hirasawa,M.Ohbayashi,J.Hu

  71. Generalization Ability of Universal Learning Network by Optimizing Network Size and Time Delay,
    Proc. of The Fourth International Conference on Neural Information Processing, November,1998
    M.Han,K.Hirasawa,M.Ohbayashi,K.Togo,J.Murata

  72. Robust Control of Nonlinear Systems for External Disturbances Using Second Order Derivatives of Using Universal Learning Network,
    Proc. of IEEE International Conference on Systems,Man and Cybernetics,Oct.1997
    M.Ohbayashi, K.Hirasawa, K.Nishimura

  73. Probablistic Universal Learning Network,
    Proc. of IEEE International Conference on Systems,Man and Cybernetics,Oct.1997
    K.Hirasawa, M.Ohbayashi,J.Murata

  74. Evaluation of multi-layered RBF Networks,
    Proc. of IEEE International Conference on Systems,Man and Cybernetics,Oct.1997
    K.Hirasawa,T.Matsuoka,M.Ohbayashi,J.Murata

  75. Stability Analysis of Universal Learning Network,
    Proc. of IEEE International Conference on Systems,Man and Cybernetics,Oct.1997
    Y.Yunqing,K.Hirasawa,M.Ohbayashi,J.Murata

  76. Nonlinear Control System with Neural Network Controller Using Rasval Learning,
    Proc. of IEEE International Conference on Systems,Man and Cybernetics,Oct.1997
    N.Shao,K.Hirasawa,M.Ohbayashi,K.Togo,J.Murata

  77. Generalization Ability of Modeling Dynamic Systems Using Universal Learning Network,
    Proc. of 11th International Federation Suymposium on System Identification,1243-1248,July,1997
    M.Han,K.HIrasawa,M.Ohbayashi,H.Fujita

  78. Holonic Control for Large-scale System,
    Proc. of 2nd Asian Control Conference,III659-662, June,1997
    N.Kusumi,K.Hirasawa,M.Ohbayashi

  79. Nonlinear Control System Using Universal Learning Network with Radial Basis Function,
    Proc. of 2nd Asian Control Conference,II19-22, June,1997
    N.Shao,K.Hirasawa,M.Ohbayashi

  80. An Escape Method from local Minimum by Orbital Correction Method at zcontroller Learning,
    Proc. of IEEE International Conference on Neural Networks,749-754,June.1997
    M.Ohbayashi,M.hashimoto,K.Hirasawa,H.Takata

  81. Nonlinear Control System with Radial Basis Function Controller Using Randam Search Method og Variable Search Length,
    Proc. of IEEE International Conference on Neural Networks,788-793,June.1997
    N.Shao,K.Hirasawa,M.Ohbayashi,K.Togo,J.Murata

  82. Robust Control for External Input Perturbation Using Second Order Derivatives of Universal Learning Network,
    Proc. of 11th Korea Automatic Control Conference, International Program,111-114,Oct.,1996
    M.Ohbayashi,K.Hirasawa

  83. Search for Optimal Time Delays in Universal Learning Network,
    Proc. of 11th Korea Automatic Control Conference, International Program,95-98,Oct.,1996
    M.Han,K.Hirasawa,M.Ohbayashi,H.Fujita

  84. Nonlinear Control System Using Universal Learning Network with Random Search Length,
    Proc. of 11th Korea Automatic Control Conference, International Program,235-238,Oct.,1996
    N.Shao,K.Hirasawa,M.Ohbayashi,K.Togo

  85. Robust Learning Control Using Universal Learning Network,
    Proc. of IEEE International Conference on Neural Networks,2208-2213,June,1996
    M.Ohbayashi,K.Hirasawa,J.Murata,M.Harada

  86. Forward Propagation Universal Learning Network,
    Proc. of IEEE International Conference on Neural Networks,353-358,June,1996
    K.Hirasawa,M.Ohbayashi,M.Koga,M.Harada

  87. Evaluation of Robust Control by Universal Learning Network,
    Proc. of First International Symposium on Artificial Life and Robotics,107-111,Feb.,1996
    M.Ohbayashi,K,Hirasawa,J.Murata

  88. Chaos Control on Multi Branch Universal Learning Network,
    Proc. of First International Symposium on Artificial Life and Robotics,112-117,Feb.,1996
    M.Koga,K,Hirasawa,J.Murata,M.Ohbayashi

  89. Universal Learning Network and Computation of its Higher Order Derivatives ,
    Proc. of IEEE International Conference on Neural Networks,1273-1277,Dec.,1995
    K.Hirasawa,M.Ohbayashi,M.Koga

  90. Chaos Control Using Second Order Derivatives of Universal Learning Network,
    Proc. of IEEE International Conference on Neural Networks,1287-1292,June,1996
    M.Koga,K.Hirasawa,J.Murata.M.Ohbayashi

  91. Learning Petri Network with Route Control,
    Proc. of IEEE International Conference on System,Man,and Cybernetics,2706-2711,Oct.,1995
    K.Hirasawa,S.Oka.S.Sakai,M.Ohbayashi,J.Murata

  92. Robust Control by Universal Learning Network,

    Proc. of 10th Korea Automatic Control Conference, Internatinal Program,123-126,Oct.,1995
    M.Ohbayashi,K.Hirasawa

  93. Likelihood Search Method with Variable Division Search,
    Proc. of 10th Korea Automatic Control Conference, Internatinal Program,114-117,Oct.,1995
    M.Koga,K.Hirasawa,J.Murata,M.Ohbauashi

  94. An Optimization Method Using Simulated Annealing for Universal Learning Network,
    Proc. of 10th Korea Automatic Control Conference, Internatinal Program,128-186,Oct.,1995
    J.Murata,A.Tajiri,K.Hirasawa,M.Ohbayashi

  95. Universal Learning Network-based Fuzzy Control,
    Proc. of 10th Korea Automatic Control Conference, Internatinal Program,436-439,Oct.,1995
    K.Hirasawa,R.Wu,M.Ohbayashi

  96. Robust Control by Universal Learning Network,
    Proc. of 10th Korea Automatic Control Conference, Internatinal Program,123-126,Oct.,1995
    M.Ohbayashi,K.Hirasawa


４．学内紀要・研究報告

  1. 20編



もとに戻る



作成日：2012.5.15