• DocumentCode
    1084715
  • Title

    On a Neural Approximator to ODEs

  • Author

    Filici, Cristian

  • Author_Institution
    Univ. de Buenos Aires, Buenos Aires
  • Volume
    19
  • Issue
    3
  • fYear
    2008
  • fDate
    3/1/2008 12:00:00 AM
  • Firstpage
    539
  • Lastpage
    543
  • Abstract
    The object of this brief is to present and analyze the training of a single-layer neural network in order to solve ordinary differential equations (ODEs). Properties of the approximator are derived and some examples of its application are shown.
  • Keywords
    approximation theory; differential equations; learning (artificial intelligence); mathematics computing; neural nets; neural approximator; ordinary differential equation; single-layer neural network training; Approximation error; Artificial neural networks; Cost function; Differential equations; Finite difference methods; Neural networks; Partial differential equations; Stability; Vectors; Error bound; neural network; ordinary differential equation (ODE); stability; Algorithms; Animals; Humans; Models, Neurological; Neural Networks (Computer); Nonlinear Dynamics;
  • fLanguage
    English
  • Journal_Title
    Neural Networks, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1045-9227
  • Type

    jour

  • DOI
    10.1109/TNN.2007.915109
  • Filename
    4459105