• DocumentCode
    1458661
  • Title

    Neural networks´ power

  • Author

    El-Sharkawi, M.A.

  • Author_Institution
    Dept. of Electr. Eng., Washington Univ., USA
  • Volume
    15
  • Issue
    5
  • fYear
    1997
  • Firstpage
    12
  • Lastpage
    15
  • Abstract
    Neural networks (NNs) are effective systems for learning pattern discriminants from a body of examples. Artificial neural networks (ANNs) have been developed in a wide variety of configurations with some common underlying characteristics. All ANNs attempt to achieve good performance via massive interconnection of simple computational elements. Neural networks are characterized by the model of their neurons, the connections among them and the methods used to train them to do specific tasks. The author describes multi-layer neural networks and Kohonen neural networks. The author then discusses how they are used in electric load forecasting and power system security assessment
  • Keywords
    load forecasting; multilayer perceptrons; power system analysis computing; power system security; self-organising feature maps; Kohonen neural networks; artificial neural networks; computational elements interconnection; electric load forecasting; multi-layer neural networks; neurons training; pattern discriminants learning; power system security assessment; Artificial neural networks; Computer networks; Hopfield neural networks; Load forecasting; Multi-layer neural network; Neural networks; Neurons; Power system harmonics; Power system security; Speech recognition;
  • fLanguage
    English
  • Journal_Title
    Potentials, IEEE
  • Publisher
    ieee
  • ISSN
    0278-6648
  • Type

    jour

  • DOI
    10.1109/45.544033
  • Filename
    544033