• DocumentCode
    1295097
  • Title

    Training partially recurrent neural networks using evolutionary strategies

  • Author

    Greenwood, Garrison W.

  • Author_Institution
    Dept. of Electr. & Comput. Sci., Western Michigan Univ., Kalamazoo, MI
  • Volume
    5
  • Issue
    2
  • fYear
    1997
  • fDate
    3/1/1997 12:00:00 AM
  • Firstpage
    192
  • Lastpage
    194
  • Abstract
    This correspondence presents the latest results of using evolutionary strategies (ESs) to design partially recurrent neural networks for viseme recognition. ESs are stochastic optimization algorithms based upon the principles of natural selection found in the biological world. Our results indicate that ESs can be effectively used to determine the synaptic weights in neural networks and can outperform backpropagation techniques
  • Keywords
    learning (artificial intelligence); recurrent neural nets; speech recognition; design; evolutionary strategies; partially recurrent neural networks training; stochastic optimization algorithms; synaptic weights; viseme recognition; Auditory system; Backpropagation algorithms; Helium; Lips; Neural networks; Pipeline processing; Recurrent neural networks; Speech recognition; Stochastic processes; Telephony;
  • fLanguage
    English
  • Journal_Title
    Speech and Audio Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1063-6676
  • Type

    jour

  • DOI
    10.1109/89.554781
  • Filename
    554781