Generative Probability Density Model in the Self-Organizing Map

  • Jouko Lampinen
  • Timo Kostiainen
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 78)


The Self-Organizing Map, SOM, is a widely used tool in exploratory data analysis. A theoretical and practical challenge in the SOM has been the difficulty to treat the method as a statistical model fitting procedure. In this chapter we give a short review of statistical approaches for the SOM. Then we present the probability density model for which the SOM training gives the maximum likelihood estimate. The density model can be used to choose the neighborhood width of the SOM so as to avoid overfitting and to improve the reliability of the results. The density model also gives tools for systematic analysis of the SOM. A major application of the SOM is the analysis of dependencies between variables. We discuss some difficulties in the visual analysis of the SOM and demonstrate how quantitative analysis of the dependencies can be carried out by calculating conditional distributions from the density model.


Density Model Voronoi Cell Conditional Density Reference Vector Distortion Function 
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.

Bibliography on Chapter 4

  1. 1.
    C. M. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, 1995Google Scholar
  2. 2.
    C. M. Bishop, M. Svensén, and C. K. I. Williams. GTM: a principled alternative to the self-organizing map. In C. von der Malsburg, W. von Seelen, J. C. Vorbruggen, and B. Sendhoff, editors, Artificial Neural Networks-ICANN 96. 1996 International Conference Proceedings, pages 165-70. Springer-Verlag, Berlin, Germany, 1996.Google Scholar
  3. 3.
    C. M. Bishop, M. Svensén, and C. K. I. Williams. GTM: The generative topographic mapping. Neural Computation, 10:215–234, 1998.Google Scholar
  4. 4.
    M. Cottrell, P. Gaubert, P. Letremy, and P. Rousset. Analyzing and representing multidimensional quantitative and qualitative data : Demographic study of the Rhone valley. the domestic consumption of the canadian families. In E. Oja and S. Kaski, editors, Kohonen Maps, pages 1–14. Elsevier, Amsterdam, 1999.Google Scholar
  5. 5.
    E. Erwin, K. Obermayer, and K. Schulten. Self-organizing maps: Ordering, convergence properties and energy functions. Biol. Cyb., 67(1):47–55, 1992.Google Scholar
  6. 6.
    T. Heskes. Energy functions for self-organizing maps. In E. Oja and S. Kaski, editors, Kohonen maps, pages 303–315. Elsevier, 1999.Google Scholar
  7. 7.
    T. Kohonen. Self-organizing formation of topologically correct feature maps. Biol. Cyb., 43(1 ):59–69, 1982.Google Scholar
  8. 8.
    T. Kohonen. Self-Organizing Maps, volume 30 of Springer Series in Information Sciences. Springer, Berlin, Heidelberg, 1995. (Second Extended Edition 1997).Google Scholar
  9. 9.
    J. Lampinen and T. Kostiainen. Overtraining and model selection with the self-organizing map. In Proc. IJCNN’99, Washington, DC, USA, July 1999.Google Scholar
  10. 10.
    J. Lampinen and A. Vehtari. Bayesian approach for neural networks - review and case studies. Neural Networks, 14(3):7–24, April 2001. (Invited article). In press.Google Scholar
  11. 11.
    S. P. Luttrell. Code vector density in topographic mappings: scalar case. IEEE Trans. on Neural Networks, 2(4):427–436, July 1991.Google Scholar
  12. 12.
    E. Oja and S. Kaski. Kohonen Maps. Elsevier, Amsterdam, 1999.Google Scholar
  13. 13.
    H. Ritter and K. Schulten. Kohonen self-organizing maps: exploring their computational capabilities. In Proc. ICNN’88 International Conference on Neural Networks, volume I, pages 109–116, Piscataway, NJ, 1988. IEEE Service Center.Google Scholar
  14. 14.
    M. E. Tipping and C. M. Bishop. Mixtures of principal component analysers. Technical report, Aston University, Birmingham B4 7ET, U.K., 1997.Google Scholar
  15. 15.
    A. Utsugi. Hyperparameter selection for self-organizing maps. Neural Computation, 9(3):623–635, 1997.Google Scholar
  16. 16.
    T. Villmann, R. Der, M. Herrmann, and T. M. Martinetz. Topology preservation in self-organizing feature maps: exact definition and measurement. IEEE Transactions on Neural Networks, 8(2):256–66, 1997.Google Scholar
  17. 17.
    I. Welling, E. Kähkönen, M. Lahtinen, K. Salmi, J. Lampinen, and T. Kostiainen. Modelling of occupants subjective responses and indoor air quality in office buildings. In Proceedings of the Ventilation 2000, 6th International Symposium on Ventilation for Contaminant Control, volume 2, pages 45–49, Helsinki, Finland, June 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Jouko Lampinen
  • Timo Kostiainen

There are no affiliations available

Personalised recommendations