• DocumentCode
    328289
  • Title

    Updating learning rates for backpropagation network

  • Author

    Zhang, Yao

  • Author_Institution
    Dept. of Marine Technol., Newcastle upon Tyne Univ., UK
  • Volume
    1
  • fYear
    1993
  • fDate
    25-29 Oct. 1993
  • Firstpage
    569
  • Abstract
    A new approach for improving the convergence rate of backpropagation network is proposed in the paper. This method updates the learning rate parameter for each individual weight before each weight is updated. Simulation on the XOR problem shows that when compared to the conventional backpropagation algorithm, the improved algorithm reduces the number of training iterations and CPU time by up to seventy and fifty times, respectively.
  • Keywords
    backpropagation; computational complexity; neural nets; XOR problem; backpropagation neural network; convergence rate; training iterations; updating learning rates; Adaptive systems; Backpropagation algorithms; Equations; Marine technology; Stability;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
  • Print_ISBN
    0-7803-1421-2
  • Type

    conf

  • DOI
    10.1109/IJCNN.1993.713979
  • Filename
    713979
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=328289