• DocumentCode
    3618382
  • Title

    An identification problem related to a continuous neural model

  • Author

    M.N. Oguztoreli

  • Author_Institution
    Dept. of Math., Alberta Univ., Edmonton, Alta., Canada
  • fYear
    1990
  • fDate
    6/12/1905 12:00:00 AM
  • Firstpage
    927
  • Lastpage
    929
  • Abstract
    The author formulates and solves an identification problem for a continuous spatio-temporal neural model that was studied earlier by M.N. Oguztoreli et al. (Biol. Cybern., vol.60, pp.89-106, 1988; and Proc. of the 1989 IEEE Conf. on Systems, Man, and Cybernetics, p.664-70) and was simulated in connection with certain visual processes. To check out the solution scheme, the solutions of the model equations were constructed using the prototype visual inputs considered in the 1988 study, and these were used as the exact solutions. The resulting values of the calculated parameters were 95% accurate.
  • Keywords
    "Neurons","Neural networks","Mathematical model","Erbium","Mathematics","Differential equations","Nonlinear equations","Pulse generation","Steady-state","History"
  • Publisher
    ieee
  • Conference_Titel
    Systems, Man and Cybernetics, 1990. Conference Proceedings., IEEE International Conference on
  • Print_ISBN
    0-87942-597-0
  • Type

    conf

  • DOI
    10.1109/ICSMC.1990.142261
  • Filename
    142261