A Parameter in the Learning Rule of SOM That Incorporates Activation Frequency

  • Antonio Neme
  • Pedro Miramontes
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)


In the traditional self-organizing map (SOM) the best matching unit (BMU) affects other neurons, through the learning rule, as a function of distance. Here, we propose a new parameter in the learning rule so neurons are not only affected by BMU as a function of distance, but as a function of the frequency of activation from both, the BMU and input vectors, to the affected neurons. This frequency parameter allows non radial neighborhoods and the quality of the formed maps is improved with respect to those formed by traditional SOM, as we show by comparing several error measures and five data sets.


Input Vector Learning Rule Error Quantization Frequency Function Learning Factor 
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.
    Cottrell, M., Fort, J.C., Pagés, G.: Theoretical aspects of the SOM algorithm. Neurocomputing 21, 119–138 (1998)MATHCrossRefGoogle Scholar
  2. 2.
    Kirk, J., Zurada, J.: A two-stage algorithm for improved topography preservation in self-organizing maps. Int. Con. on Sys., Man and Cyb. 4, 2527–2532 (2000)Google Scholar
  3. 3.
    Haykin, S.: Neural Networks, a comprehensive foundation, 2nd edn. Prentice Hall, Englewood Cliffs (1999)MATHGoogle Scholar
  4. 4.
    Kohonen, T.: Self-Organizing maps, 3rd edn. Springer, Heidelberg (2000)Google Scholar
  5. 5.
    Flanagan, J.: Sufficiente conditions for self-organization in the SOM with a decreasing neighborhood function of any width. Conf. of Art. Neural Networks. Conf. pub. No. 470 (1999)Google Scholar
  6. 6.
    Erwin, E., Obermayer, K., Schulten, K.: Self-organizing maps: Ordering, convergence properties and energy functions. Biol. Cyb. 67, 47–55 (1992)MATHCrossRefGoogle Scholar
  7. 7.
    Ritter, H.: Self-Organizing Maps on non-euclidean Spaces Kohonen Maps. In: Oja, E., Kaski, S. (eds.), pp. 97–108 (1999)Google Scholar
  8. 8.
    Lee, J., Verleysen, M.: Self-organizing maps with recursive neighborhood adaption. Neural Networks 15, 993–1003 (2002)CrossRefGoogle Scholar
  9. 9.
    Campoy, P., Vicente, C.: Residual Activity in the Neurons Allows SOMs to Learn Temporal Order. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 379–384. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Chappell, G., Taylor, J.: The temporal Kohonen map. Neural Networks 6, 441–445 (1993)CrossRefGoogle Scholar
  11. 11.
    Kiviluoto, K.: Topology preservation in Self-Organizing maps. In: Proc. ICNN 1996, IEEE Int. Conf. on Neural Networks (1996)Google Scholar
  12. 12.
    Venna, J., Kaski, S.: Neighborhood preservation in nonlinear projection methods: An experimental studyGoogle Scholar
  13. 13.
    Lamm, C., Leodolter, U., Moser, E., Bauer, H.: Evidence for premotor cortex activity during dynamic visuospatial imaginery. Neuroimage 14, 268–283 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Antonio Neme
    • 1
    • 2
  • Pedro Miramontes
    • 2
  1. 1.Department of Nonlinear Dynamics and Complex SystemsUniversidad Autónoma de la Ciudad de MéxicoMéxico
  2. 2.Facultad de CienciasUniversidad Nacional Autónoma de MéxicoMéxico

Personalised recommendations