Biological Cybernetics

, Volume 64, Issue 2, pp 95–105 | Cite as

Self-organization of associative memory and pattern classification: recurrent signal processing on topological feature maps

  • P. Tavan
  • H. Grubmüller
  • H. Kühnel


We extend the neural concepts of topological feature maps towards self-organization of auto-associative memory and hierarchical pattern classification. As is well-known, topological maps for statistical data sets store information on the associated probability densities. To extract that information we introduce a recurrent dynamics of signal processing. We show that the dynamics converts a topological map into an auto-associative memory for real-valued feature vectors which is capable to perform a cluster analysis. The neural network scheme thus developed represents a generalization of non-linear matrix-type associative memories. The results naturally lead to the concept of a feature atlas and an associated scheme of self-organized, hierarchical pattern classification.


Neural Network Cluster Analysis Signal Processing Probability Density Feature Vector 
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. Knudsen EI, du Lac S, Esterly SD (1987) Computational maps in the brain. Ann Rev Neurosci 10:41–65PubMedGoogle Scholar
  2. Kohonen T (1982a) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69CrossRefGoogle Scholar
  3. Kohonen T (1982b) Analysis of a simple self-organizing process. Biol Cybern 44:135–140CrossRefGoogle Scholar
  4. Kohonen T (1984) Self-organization and associative memory. Springer, Berlin Heidelberg New YorkGoogle Scholar
  5. Kosko B (1988) Bidirectional associative memories. IEEE Trans Syst Man Cybern 18:49–60CrossRefGoogle Scholar
  6. Kühnel H (1990) Diplomarbeit, Physik-Department, Technische Universität MünchenGoogle Scholar
  7. Linde Y, Buzo A, Gray RM (1980) An algorithm for vector quantizer design. IEEE Trans Comm 28:84–95CrossRefGoogle Scholar
  8. Malsburg C von der, Willshaw DJ (1977) How to label nerve cells so that they can interconnect in an ordered fashion. Proc Natl Acad Sci USA 74:5176–5178PubMedGoogle Scholar
  9. Ritter H (1989) Asymptotic level density for a class of vector quantization processes. Technical Report, University of HelsinkiGoogle Scholar
  10. Ritter H, Kohonen T (1989) Self-organizing semantic maps. Biol Cybern 61:241–254CrossRefGoogle Scholar
  11. Ritter H, Schulten K (1988a) Extending Kohonen's self-organizing mapping algorithm to learn ballistic movements. In: Eckmiller R, Malsburg C von der (eds) Neural computers. Springer, Berlin Heidelberg New York, pp 393–406Google Scholar
  12. Ritter H, Schulten K (1988b) Kohonen's self-organizing maps: exploring their computational capabilities. IEEE ICNN 88 Conference, San Diego, pp 109–116Google Scholar
  13. Willshaw DJ, Malsburg C von der, (1976) How patterned neural connections can be set up by self-organization. Proc R Soc London B 194:431–445Google Scholar

Copyright information

© Springer-Verlag 1990

Authors and Affiliations

  • P. Tavan
    • 1
  • H. Grubmüller
    • 1
  • H. Kühnel
    • 1
  1. 1.Physik-DepartmentTechnische Universität MünchenGarchingFederal Republic of Germany

Personalised recommendations