• DocumentCode
    314280
  • Title

    Accelerating backpropagation in human face recognition

  • Author

    Evans, D.J. ; Ahmad Fadzil, M.H. ; Zainuddin, Zahir

  • Author_Institution
    Dept. of Comput. Studies, Loughborough Univ. of Technol., UK
  • Volume
    3
  • fYear
    1997
  • fDate
    9-12 Jun 1997
  • Firstpage
    1347
  • Abstract
    Standard backpropagation, as with many gradient based optimization methods converges slowly as neural network training problems become larger and more complex. This paper describes the employment of two algorithms to accelerate the training procedure in an automatic human face recognition system. As compared to standard backpropagation, the convergence rate is improved by up to 98% with only a minimal increase in the complexity of each iteration
  • Keywords
    backpropagation; convergence; face recognition; image classification; multilayer perceptrons; optimisation; visual databases; backpropagation; convergence rate; gradient based optimization methods; human face recognition; neural network training problems; Acceleration; Appropriate technology; Convergence; Employment; Face recognition; Humans; Neural networks; Neurons; Optimization methods; Pixel;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks,1997., International Conference on
  • Conference_Location
    Houston, TX
  • Print_ISBN
    0-7803-4122-8
  • Type

    conf

  • DOI
    10.1109/ICNN.1997.613974
  • Filename
    613974