• DocumentCode
    1409839
  • Title

    A unified approach on fast training of feedforward and recurrent networks using EM algorithm

  • Author

    Ma, Sheng ; Ji, Chuanyi

  • Author_Institution
    Dept. of Electr. Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
  • Volume
    46
  • Issue
    8
  • fYear
    1998
  • fDate
    8/1/1998 12:00:00 AM
  • Firstpage
    2270
  • Lastpage
    2274
  • Abstract
    In this work, we provide a theoretical framework that unifies the notions of hidden representations and moving targets through the expectation and maximization (EM) algorithm. Based on such a framework, two fast training algorithms can be derived consistently for both feedforward networks and recurrent networks
  • Keywords
    feedforward neural nets; learning (artificial intelligence); random processes; recurrent neural nets; signal representation; EM algorithm; expectation and maximization algorithm; fast training algorithms; feedforward networks; hidden representations; moving targets; recurrent networks; unified approach; Heuristic algorithms; Joining processes; Maximum likelihood estimation; Multi-layer neural network; Nonhomogeneous media; Recurrent neural networks; Signal processing; Signal processing algorithms; Speech processing; Statistics;
  • fLanguage
    English
  • Journal_Title
    Signal Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1053-587X
  • Type

    jour

  • DOI
    10.1109/78.705464
  • Filename
    705464