• DocumentCode
    771347
  • Title

    High-order absolutely stable neural networks

  • Author

    Dembo, Amir ; Farotimi, Oluseyi ; Kailath, Thomas

  • Author_Institution
    Dept. of Electr. Eng., Stanford Univ., CA, USA
  • Volume
    38
  • Issue
    1
  • fYear
    1991
  • fDate
    1/1/1991 12:00:00 AM
  • Firstpage
    57
  • Lastpage
    65
  • Abstract
    The stability properties of arbitrary order continuous-time dynamic neural networks are studied in the spirit of an earlier analysis of a first-order system by M.A. Cohen and S. Grossberg (1983). The corresponding class of Lyapunov function is presented and the equilibrium points are characterized. The relationships with other continuous-time models are pointed out
  • Keywords
    Lyapunov methods; convergence; neural nets; polynomials; stability; Lyapunov function; arbitrary order; continuous-time; dynamic networks; equilibrium points; high order type; neural networks; stability properties; Associative memory; Circuit stability; Circuits and systems; Linear programming; Lyapunov method; Neural networks; Neurons; Pattern recognition; Stability analysis; State estimation;
  • fLanguage
    English
  • Journal_Title
    Circuits and Systems, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0098-4094
  • Type

    jour

  • DOI
    10.1109/31.101303
  • Filename
    101303