• DocumentCode
    1416047
  • Title

    Adaptive algorithm for training pRAM neural networks on unbalanced data sets

  • Author

    Ramanan, S. ; Clarkson, T.G. ; Taylor, J.G.

  • Author_Institution
    Dept. of Electron. Syst. Eng., Essex Univ., Colchester, UK
  • Volume
    34
  • Issue
    13
  • fYear
    1998
  • fDate
    6/25/1998 12:00:00 AM
  • Firstpage
    1335
  • Lastpage
    1336
  • Abstract
    A novel algorithm for training pyramidal pRAM neural networks on an unbalanced training set is proposed. The behaviour of the standard reinforcement learning algorithm is analysed and an adaptive learning rate algorithm that modifies the reinforcement learning algorithm based on readily available a priori class probability is developed
  • Keywords
    feedforward neural nets; learning (artificial intelligence); a priori class probability; adaptive learning rate algorithm; feedforward neural nets; pyrimidal pRAM neural networks; standard reinforcement learning algorithm; unbalanced data sets;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19980921
  • Filename
    707251
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1416047