• DocumentCode
    1403500
  • Title

    Existence, learning, and replication of periodic motions in recurrent neural networks

  • Author

    Ruiz, A. ; Owens, David H. ; Townley, Stuart

  • Author_Institution
    Centre for Syst. & Control Eng., Exeter Univ., UK
  • Volume
    9
  • Issue
    4
  • fYear
    1998
  • fDate
    7/1/1998 12:00:00 AM
  • Firstpage
    651
  • Lastpage
    661
  • Abstract
    A class of recurrent neural networks is shown to possess a stable limit cycle. A gradient type algorithm is used to modify the parameters of the network so that it learns and replicates autonomously a time varying periodic signal. The results are applied to controlling the repetitive motion of a two-link robot manipulator
  • Keywords
    learning (artificial intelligence); limit cycles; recurrent neural nets; stability; time-varying systems; gradient type algorithm; parameter modification; periodic motion learning; periodic motion replication; recurrent neural networks; repetitive motion; stable limit cycle; time varying periodic signal; two-link robot manipulator; Bifurcation; Control engineering; Intelligent networks; Learning systems; Limit-cycles; Manipulator dynamics; Motion control; Neural networks; Recurrent neural networks; Robots;
  • fLanguage
    English
  • Journal_Title
    Neural Networks, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1045-9227
  • Type

    jour

  • DOI
    10.1109/72.701178
  • Filename
    701178