• DocumentCode
    2812744
  • Title

    Adaptive three-dimensional self-organizing map with a two-dimensional input layer

  • Author

    Seiffert, Udo ; Michaelis, Bernd

  • Author_Institution
    Inst. for Meas. Technol. & Electron., Otto-von-Guericke Univ. of Magdeburg, Germany
  • fYear
    1996
  • fDate
    18-20 Nov 1996
  • Firstpage
    258
  • Lastpage
    263
  • Abstract
    This paper introduces an adaptive growing three-dimensional self-organizing map with the special feature of a matrix input layer instead of a one-dimensional vector. First a short description of growing SOMs is given and the fundamental advantages are mentioned. Then an extension of the original SOM from two to three dimensions with a growing feature is presented. By means of a selected example the general behaviour of the algorithm is illustrated
  • Keywords
    adaptive systems; learning (artificial intelligence); matrix algebra; self-organising feature maps; vectors; adaptive three-dimensional self-organizing map; growing SOM; growing feature; matrix input layer; one-dimensional vector; two-dimensional input layer; Australia; Biological systems; Euclidean distance; Intelligent structures; Intelligent systems; Neurons; Self organizing feature maps; Sorting; Topology; World Wide Web;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Information Systems, 1996., Australian and New Zealand Conference on
  • Conference_Location
    Adelaide, SA
  • Print_ISBN
    0-7803-3667-4
  • Type

    conf

  • DOI
    10.1109/ANZIIS.1996.573952
  • Filename
    573952