• DocumentCode
    2041201
  • Title

    A liked-BAM neural network for image recognition

  • Author

    Shen, D.G. ; Qi, F.H.

  • Author_Institution
    Res. Inst. of Optical Fibre Eng., Shanghai Jiaotong Univ., China
  • Volume
    2
  • fYear
    1993
  • fDate
    19-21 Oct. 1993
  • Firstpage
    966
  • Abstract
    A neural network model and its application to image recognition are proposed in this paper. This model consists of a mapping network (MN) and liked bidirectional associative memory (LBAM). Invariant mapping is used in MN in order to decrease the number of dimensions of image samples and not to change the distance between them. LBAM´s structure is simple and its convergence speed is fast.<>
  • Keywords
    content-addressable storage; image recognition; learning (artificial intelligence); neural nets; computer simulations; convergence speed; image recognition; image samples; invariant mapping; liked bidirectional associative memory; liked-BAM neural network; mapping network; noise-added targets; Acceleration; Application software; Associative memory; Computer simulation; Convergence; Equations; Image recognition; Neural networks; Optical fibers; Target recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
  • Conference_Location
    Beijing, China
  • Print_ISBN
    0-7803-1233-3
  • Type

    conf

  • DOI
    10.1109/TENCON.1993.320174
  • Filename
    320174