A SOM Association Network

  • T. Yamakawa
  • K. Horio
  • R. Kubota
Conference paper


In this paper, we propose a self-organizing map association (SOMA) network which associates a perfect information from a part of the information. The processes of the SOMA network are divided into a learning mode and an association mode. In the learning mode, the similar perfect informations are represented by a few units on the competitive layer. In the association mode, when the information, whose parts are lost, is applied to the SOMA network, the lost part is associated. The performance of the SOMA network is evaluated by applying to the association of the data used in the orthodontics.


Weight Vector Input Vector Input Layer Perfect Information Learning Mode 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    T. Kohonen, “Self-organized formation of topologically correct feature maps”, Biol. Cybern., Vol.43, pp.59-69, 1982.MathSciNetMATHCrossRefGoogle Scholar
  2. [2]
    T.Kohonen, Self-organization and associative memory, Second edition, Berlin: Springer-Verlag, 1988.MATHGoogle Scholar
  3. [3]
    Legan HL, Burstone CJ, “Soft tissue cephalometric analysis for orthognathic surgery”, J Oral Sung, Vol. 38, pp. 744-751, 1980.Google Scholar

Copyright information

© Springer-Verlag London Limited 2001

Authors and Affiliations

  • T. Yamakawa
    • 1
    • 2
  • K. Horio
    • 1
  • R. Kubota
    • 3
  1. 1.Department of Brain Science and EngineeringKyushu Institute of Technologyiizuka, FukuokaJapan
  2. 2.Fuzzy Logic Systems Institute (FLSI)IizukaJapan
  3. 3.Department of Control Engineering and ScienceKyushu Institute of TechnologyIizuka, FukuokaJapan

Personalised recommendations