• DocumentCode
    1601521
  • Title

    Adapted gradient algorithm for algebraic fuzzy neural networks

  • Author

    Teodorescu, H.N. ; Arotaritei, D. ; Gonzalez, E.L. ; Mendana, A.

  • Author_Institution
    Tech. Univ. Iasi, Romania
  • fYear
    1996
  • Firstpage
    179
  • Lastpage
    186
  • Abstract
    A learning algorithm based on a gradient technique is introduced for the algebraic fuzzy neural network with fuzzy weights. The fuzzy weights can be triangular fuzzy numbers (usually nonsymmetric), or trapezoidal fuzzy numbers. The network is able to map a vector of triangular (trapezoidal) fuzzy numbers into any other vector of triangular (trapezoidal) fuzzy numbers
  • Keywords
    fuzzy neural nets; learning (artificial intelligence); vectors; adapted gradient algorithm; algebraic fuzzy neural networks; fuzzy weights; learning algorithm; nonsymmetric triangular fuzzy numbers; trapezoidal fuzzy numbers; vector; Arithmetic; Costs; Electronic mail; Fuzzy neural networks; Fuzzy sets; Level set; Multi-layer neural network; Neural networks; Neurons; Shape;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neuro-Fuzzy Systems, 1996. AT'96., International Symposium on
  • Conference_Location
    Lausanne
  • Print_ISBN
    0-7803-3367-5
  • Type

    conf

  • DOI
    10.1109/ISNFS.1996.603837
  • Filename
    603837