Supervised Classification with Associative SOM

  • Rafael del-Hoyo
  • David Buldain
  • Alvaro Marco
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2686)

Abstract

This paper presents an extension of the Self Organizing Map model called Associative SOM that is able to process different types of input data in separated data-paths. The ASOM model can easily deal with situations of incomplete data-patterns and incorporate class labels for supervisory purposes. The ASOM is successfully compared with Multilayer Perceptrons in the incremental classification of six erythemato-squamous diseases, where only partial data is available in successive steps.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.D. Buldain, A. Roy: Association with Multi-Dendritic Radial Basis Units. IWANN 99, Lecture Notes in Computer Science 1606, Foundations and Tools for Neural Modeling (1999)573–581Google Scholar
  2. 2.
    H.A. Güvenir, G. Demiröz and N. liter,: Learning Differential Diagnosis of Erythemalo-Squamous Diseases using Voting Feature Intervals. Artificial Intelligence in Medicine,Vol. 13, No. 3 (1998) 147–165CrossRefGoogle Scholar
  3. 3.
    T. Kohonen. The self-organizing map. In Proc. IEEE, volumen 78, pages 1464–1480,1990.Google Scholar
  4. 4.
    T. Kohonen. Self-Organization and Associative Memory, Springer Series In Information Sciences 8. Springer, Heidelberg, 1984.Google Scholar
  5. 5.
    H. Ritter. Parametrized selft-organizing maps. In S. Gielen and B. Kappen, editors, ICANN93-Proceddings, Amsterdam, pages 568–575. Springer Verlag, Berlin, 1993.Google Scholar
  6. 6.
  7. 7.

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Rafael del-Hoyo
    • 1
  • David Buldain
    • 2
  • Alvaro Marco
    • 1
  1. 1.Institute Tecnológico de Arag’onZaragozaSpain
  2. 2.Departamento de Electrónica y ComunicacionesUniversity of ZaragossaZaragozaSpain

Personalised recommendations