• DocumentCode
    851213
  • Title

    Analogue recurrent neural network for linear algebraic equation solving

  • Author

    Yi, Changyan ; Zhang, Ye

  • Author_Institution
    Sch. of Inf. Sci. & Technol., Sun Yat-Sen Univ., Guangzhou
  • Volume
    44
  • Issue
    18
  • fYear
    2008
  • Firstpage
    1078
  • Lastpage
    1079
  • Abstract
    A new recurrent neural network (RNN) is presented for solving online linear time-invariant (LTI) equations, which has been developed based ingeniously on a vector-valued error-function rather than a scalar-valued norm-based function. Theoretical analysis and simulation results both substantiate the efficacy of such an RNN model for online LTI equation solving.
  • Keywords
    T invariance; algebra; neural nets; online linear time-invariant equations; recurrent neural network; scalar- valued norm-based function; vector-valued error-function;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:20081390
  • Filename
    4610681
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=851213