• DocumentCode
    1521178
  • Title

    Competitive neural network scheme for learning vector quantisation

  • Author

    Wang, Jung-Hua ; Peng, Chung-Yun

  • Author_Institution
    Dept. of Electr. Eng., Nat. Taiwan Ocean Univ., Keelung, Taiwan
  • Volume
    35
  • Issue
    9
  • fYear
    1999
  • fDate
    4/29/1999 12:00:00 AM
  • Firstpage
    725
  • Lastpage
    726
  • Abstract
    A novel self-development neural network scheme, which employs two resource counters to record node activity, is presented. The proposed network not only harmonises equi-error and equi-probable criteria, but it also avoids the stability-and-plasticity dilemma. Simulation results show that the new scheme displays superior performance (in terms of measured MSE, MAE, and training speed) over other neural network models
  • Keywords
    mean square error methods; neural nets; unsupervised learning; vector quantisation; MAE; MSE; competitive neural network scheme; equi-error criteria; equi-probable criteria; learning vector quantisation; mean absolute error; node activity; resource counters; self-development neural network scheme; training speed;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19990505
  • Filename
    769852
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1521178