• DocumentCode
    2220600
  • Title

    A novel learning law for a single neuron

  • Author

    Shin, Seiichi ; Shiozawa, Yoichi

  • Author_Institution
    Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
  • fYear
    1993
  • fDate
    15-19 Nov 1993
  • Firstpage
    293
  • Abstract
    In this paper, the learning gain is reconsidered from the viewpoint of the adaptive control systems. We present a novel learning law for a single neuron, which is a kind of σ-modified adaptive law used in the robust adaptive control systems. We presents a brief proof of boundedness of the estimator to be learned and a simple numerical simulation, where we show the viability of the proposed learning law
  • Keywords
    adaptive systems; learning (artificial intelligence); neural nets; parameter estimation; adaptive control systems; adaptive law; boundedness; learning gain; learning law; neural nets; neuron; robust control; Adaptive control; Convergence; Facsimile; Information science; Neural networks; Neurons; Numerical simulation; Physics; Programmable control; Robust control;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Electronics, Control, and Instrumentation, 1993. Proceedings of the IECON '93., International Conference on
  • Conference_Location
    Maui, HI
  • Print_ISBN
    0-7803-0891-3
  • Type

    conf

  • DOI
    10.1109/IECON.1993.339064
  • Filename
    339064