• DocumentCode
    1680513
  • Title

    Multiplier-free feedforward networks

  • Author

    Khan, Altaf H.

  • Volume
    3
  • fYear
    2002
  • fDate
    6/24/1905 12:00:00 AM
  • Firstpage
    2698
  • Lastpage
    2703
  • Abstract
    A feedforward network is proposed which lends itself to cost-effective implementations in digital hardware and has a fast forward-pass capability. It differs from the conventional model in restricting its synapses to the set {-1, 0, 1} while allowing unrestricted offsets. Simulation results on the ´onset of diabetes´ data set and a handwritten numeral recognition database indicate that the new network, despite having strong constraints on its synapses, has a generalization performance similar to that of its conventional counterpart
  • Keywords
    feedforward neural nets; diabetes; digital hardware; fast forward-pass capability; feedforward neural network; generalization; handwritten numeral recognition database; multiplier-free feedforward networks; synapses; unrestricted offsets; Arithmetic; Computer architecture; Equations; Hardware; Machine learning; Neurons; Spatial databases; Very large scale integration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
  • Conference_Location
    Honolulu, HI
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7278-6
  • Type

    conf

  • DOI
    10.1109/IJCNN.2002.1007573
  • Filename
    1007573