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

2003 Fiscal Year Final Research Report Summary

An autonomous system with inner modeled associative memory

Research Project

Project/Area Number 13450176
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Control engineering
Research InstitutionYamaguchi University

Principal Investigator

OBAYASHI Masanao  Yamaguchi University, Faculty of Engineering, Professor, 工学部, 教授 (60213849)

Co-Investigator(Kenkyū-buntansha) KUREMOTO Takashi  Yamaguchi University, Faculty of Engineering, Research Assistant, 工学部, 教務員 (40294657)
KOBAYASHI Kunikazu  Yamaguchi University, Faculty of Engineering, Research Associate, 工学部, 助手 (40263793)
Project Period (FY) 2001 – 2003
KeywordsLearning / Chaotic Neural network / Reinforcement Learning / Nonlinear system control / Chaos / Edge of chaos / Associative memory / Robot
Research Abstract

To realize the autonomous system with inner modeled associative memory, it is very useful to research the function of the human brain and learning method of the living things. Under these considerations, we mainly developed
i) for reinforcement learning, a faster learning method with asymmetric probability density function to realize trial and error effectively
ii) for reinforcement learning, a learning method introducing the idea of time-varying parameters in order to adapt to dynamical environments which change rapidly
iii) chaotic neural networks with function typed synaptic weights which enable easier retrieval of stored patterns than conventional in the case that each stored patterns have strong correlation each other
iv) a retrieval method for time-series data, particularly for plural time-series data which have same first data but different after that
v) robust chaotic control method introducing the idea of edge of chaos that the system is in the state between chaotic state and non-chaotic state
vi) high precision of chaotic time series prediction by introducing the stochastic ascent gradient reinforcement learning method as prediction method
These validity has been clarified by simulation studies

  • Research Products

    (18 results)

All Other

All Publications (18 results)

  • [Publications] 梅迫公輔: "適応的探索法を用いた強化学習"電気学会論文誌. 122-C. 374-380 (2002)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 大林正直: "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. 38-10. 907-914 (2002)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 梅迫公輔: "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)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 大林正直: "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. 1631-1637 (2003)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 梅迫公輔: "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(印刷中). (2004)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Takashi Kuremoto: "Predicting Chaotic Time Series by Reinforcement Learning"Proceedings of International Conference on computational Intelligence, Robotics and Autonomous Systems. (CDROM). (2003)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] K.Umesako: "Reinforcement Learning Using Adaptive Search-Method"Transactions of Institute of Electrical Engineers of Japan. Vol.22-C, No.3. 374-380 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] M.Obayashi: "Chaotic System Control Considering Edge of Chaos Using Neural Network"Transaction of Society of Instrument and Control Engineers. Vol.38, No.10. 907-914 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Umesako: "Self-Organized Fuzzy Reinforcement Learning-System"Transactions of Society of Instrument and Control Engineers. Vol.39, No7. 699-701 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] M.Obayashi: "Associative Memory and Mutual Information In a Chaotic Neural Network Introducing Function Typed Synaptic Weights"Transactions of Institute of Electrical Engineers of Japan. Vol.123, No.9. 1631-1637 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Umesako: "Evolutionary Reinforcement Learning System with Time-Varying Parameters"Transactions of Institute of Electrical Engineers of Japan. Vol.124, No.7 (in press). (2004)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Umesako: "Fast Reinforcement Learning Using Asymmetric Probability Density Function"Proc.of 41^<st> Society of Instrument and Control Engineering Annual Conference. 907-912 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Kobayashi: "A chaotic memory search model based on associative dynamics using features in stored patterns"Proc.of 41^<st> Society of Instrument and Control Engineering Annual Conference. 2919-2924 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Umesako: "Mobile robot control using self-organized fuzzy reinforcement learning system"Proc.of International Symposium on Advanced Control of Industrial Processes. 513-519 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] M.Obayashi: "Actor-Critic Reinforcement Learning System with Time-Varying Parameters"Proc.of the International Conference on Control, Automation and System. 138-141 (2002)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] T Kuremoto: "Predicting Chaotic Time Series by Reinforcement Learning"Proc.of the 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems. (CD-ROM). (2003)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.Umesako: "Evolutionary and time-varying reinforcement learning system based on overlap of rules"Proc.of 6th Japan-France Congress on Mechatronics and 4th Asia-Europe Congress on Mechatronics. 202-207 (2003)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] M.Obayashi: "Reinforcement Learning System with Time Varying Parameters Using Neural Network"Proc.of the 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications. (in press). (2003)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 2005-04-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi