• DocumentCode
    2308024
  • Title

    On tensor-product model based representation of neural networks

  • Author

    Rövid, András ; Szeidl, László ; Várlaki, Péter

  • Author_Institution
    John von Neumann Fac. of Infomatics, Obuda Univ., Budapest, Hungary
  • fYear
    2011
  • fDate
    23-25 June 2011
  • Firstpage
    69
  • Lastpage
    72
  • Abstract
    The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.
  • Keywords
    approximation theory; neural nets; singular value decomposition; tensors; approximation methods; complex parameter varying model; higher order singular value decomposition; neural network representation; tensor-product model; Analytical models; Approximation methods; Artificial neural networks; Mathematical model; Numerical models; Singular value decomposition; Tensile stress;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Engineering Systems (INES), 2011 15th IEEE International Conference on
  • Conference_Location
    Poprad
  • Print_ISBN
    978-1-4244-8954-1
  • Type

    conf

  • DOI
    10.1109/INES.2011.5954721
  • Filename
    5954721