• DocumentCode
    2849091
  • Title

    The Problems and Its Analysis of BP Neural Network

  • Author

    Wang Jiquan ; Qiu Lichun ; Liu Guilian ; Wang Fulin

  • Volume
    2
  • fYear
    2010
  • fDate
    13-14 Oct. 2010
  • Firstpage
    701
  • Lastpage
    704
  • Abstract
    This paper makes further research on BP neural network algorithm on the basis of the existing literature. It pointed out the problems in the inherent algorithm, as well as the causes were presented. This research also proposed the BP neural network was difficult to achieve the desired effect when applied to solve the forecasting problems, and then the reasons of that were analyzed, and this point was verified by sampling calculations. all these results will establish the foundation for further research of BP neural network algorithm.
  • Keywords
    backpropagation; forecasting theory; neural nets; sampling methods; BP neural network; forecasting problem; inherent algorithm; sampling calculation; Algorithm design and analysis; Artificial neural networks; Convergence; Data processing; Forecasting; Training; Transfer functions; BP neural network; fluctuate; forecasting; oscillate;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent System Design and Engineering Application (ISDEA), 2010 International Conference on
  • Conference_Location
    Changsha
  • Print_ISBN
    978-1-4244-8333-4
  • Type

    conf

  • DOI
    10.1109/ISDEA.2010.415
  • Filename
    5743507