• DocumentCode
    2972689
  • Title

    Improving the back propagation learning speed with adaptive neuro-fuzzy technique

  • Author

    Huang, Yo-Ping ; Chang, Chih Cheng ; Huang, Chi Chang

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Tatung Inst. of Technol., Taipei, Taiwan
  • Volume
    3
  • fYear
    1993
  • fDate
    25-29 Oct. 1993
  • Firstpage
    2897
  • Abstract
    A neuro-fuzzy technique is presented to improve the standard back propagation learning speed. By adjusting both the learning rate and accelerator parameters based on the system error and change of the error direction, the convergent rate of the proposed technique is found to be superior to that yielded by the conventional approach. Simulation results are given to demonstrate the applicability and efficiency of the proposed method.
  • Keywords
    backpropagation; feedforward neural nets; multilayer perceptrons; pattern recognition; adaptive neuro-fuzzy technique; backpropagation learning speed; convergent rate; error direction; learning rate; Computational complexity; Computer errors; Computer science; Fuzzy neural networks; Joining processes; Neural networks; Neurons; Probes; System testing;
  • 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.1993.714328
  • Filename
    714328