• DocumentCode
    3254912
  • Title

    Effect of sinusoidal function on backpropagation learning

  • Author

    Karimi, Bijan ; Ashenayi, Kaveh ; Seyed, Taraneh Baradaran

  • Author_Institution
    New Haven Univ., CT, USA
  • fYear
    1992
  • fDate
    6-9 Apr 1992
  • Firstpage
    9
  • Lastpage
    12
  • Abstract
    The backpropagation (BP) method is modified by replacing the sigmoid function by a sinusoidal function. The leaving law is also modified. The modified procedure shows great improvement over the original BP in terms of the number of neurons and the learning time
  • Keywords
    backpropagation; neural nets; backpropagation learning; learning time; leaving law; neurons; sinusoidal function; Artificial neural networks; Backpropagation; Brain modeling; Character recognition; Computer networks; Equations; Frequency; Humans; Neural networks; Neurons;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Simulation Symposium, 1992. Proceedings., 25th Annual
  • Conference_Location
    Orlando, FL
  • Print_ISBN
    0-8186-2765-4
  • Type

    conf

  • DOI
    10.1109/SIMSYM.1992.227582
  • Filename
    227582
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3254912