Self-Organizing Maps of Spiking Neurons Using Temporal Coding

  • Berthold Ruf
  • Michael Schmitt


Kohonen’s self-organizing map has been thoroughly investigated for artificial neural networks. There have been several approaches for biologically more realistic neural networks which all rely on rate coding. Here we show that a topology preserving behavior can be also achieved by networks of spiking neurons using temporal coding. Besides being generally faster during learning and application, our approach has the additional advantage that the winner among competing neurons can be determined fast and locally. Our model is a further step towards a more realistic description of unsupervised learning in biological neural systems. Furthermore, it may provide a basis for fast implementations of neural networks in pulsed VLSI.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    W. Gerstner and L. van Hemmen. How to describe neuronal activity: spikes, rates or assemblies? In Advances in Neural Information Processing Systems, volume 6. Morgan Kaufmann, 1994.Google Scholar
  2. 2.
    T. Sejnowski. Time for a new neural code? Nature, 376: 21–22, 1995.PubMedCrossRefGoogle Scholar
  3. 3.
    F. Rieke, D. Warland, W. Bialek, and R. de Ruyter van Steveninck. SPIKES: Exploring the Neural Code. MIT-Press, Cambridge, 1996.Google Scholar
  4. 4.
    W. Maass. Networks of spiking neurons: The third generation of neural network models. To appear in: Neural Networks.Google Scholar
  5. 5.
    M. A. Arbib, editor. The Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge, 1995.Google Scholar
  6. 6.
    W. Maass. Lower bounds for the computational power of networks of spiking neurons. Neural Computation, 8: 1–40, 1996.CrossRefGoogle Scholar
  7. 7.
    B. Ruf and M. Schmitt. Learning temporally encoded patterns in networks of spiking neurons. Neural Processing Letters, 5(1): 9–18, 1997.CrossRefGoogle Scholar
  8. 8.
    W. Maass. Fast sigmoidal networks via spiking neurons. Neural Computation, 9: 279–304, 1997.PubMedCrossRefGoogle Scholar
  9. 9.
    T. Kohonen. Self-Organizing Maps. Springer, Berlin, 1995.CrossRefGoogle Scholar
  10. 10.
    T. Kohonen. Physiological interpretation of the self-organizing map algorithm. Neural Networks, 6: 895–905, 1993.Google Scholar
  11. 11.
    J. Sirosh and R. Miikkulainen. Topographic receptive fields and patterned lateral interaction in a self-organizing model of the primary visual cortex. Neural Computation, 9: 577–594, 1997.PubMedCrossRefGoogle Scholar
  12. 12.
    Y. Choe and R. Miikkulainen. Self-organization and segmentation with laterally connected spiking neurons. Technical Report AI TR 96–251, Department of Computer Science, University of Texas at Austin, 1996.Google Scholar
  13. 13.
    A. Murray and L. Tarassenko. Analogue Neural VLSI: A Pulse Stream Approach. Chapman & Hall, 1994.Google Scholar
  14. 14.
    B. Ruf and M. Schmitt. Unsupervised learning in networks of spiking neurons using temporal coding. In W. Gerstner, A. Germond, M. Hasler, and J.-D. Nicoud, editors, Proceedings of the 7th International Conference on Artificial Neural Networks — ICANN97, volume 1327 of Lecture Notes in Computer Science, pages 361–366, Springer, Berlin, 1997.Google Scholar
  15. 15.
    G. J. Goodhill and T. J. Sejnowski. A unifying objective function for topographic mappings. Neural Computation, 9: 1291–1303, 1997.CrossRefGoogle Scholar
  16. 16.
    B. Ruf. Computing functions with spiking neurons in temporal coding. In J. Mira, R. Moreno-Diaz, and J. Cabestany, editors, Biological and Artificial Computation: From Neuroscience to Technology, volume 1240 of Lecture Note in Computer Science, pages 265–272. Springer, Berlin, 1997.Google Scholar

Copyright information

© Springer Science+Business Media New York 1998

Authors and Affiliations

  • Berthold Ruf
    • 1
  • Michael Schmitt
    • 1
  1. 1.Institute for Theoretical Computer ScienceTechnische Universität GrazGrazAustria

Personalised recommendations