Advertisement

Tempotron-Like Learning with ReSuMe

  • Răzvan V. Florian
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5164)

Abstract

The tempotron is a model of supervised learning that allows a spiking neuron to discriminate between different categories of spike trains, by firing or not as function of the category. We show that tempotron learning is quasi-equivalent to an application for a specific problem of a previously proposed, more general and biologically plausible, supervised learning rule (ReSuMe). Moreover, we show through simulations that by using ReSuMe one can train neurons to categorize spike trains not only by firing or not, but also by firing given spike trains, in contrast to the original tempotron proposal.

Keywords

Spike Train Input Pattern Learning Rule Spike Time Random Initial Condition 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gütig, R., Sompolinsky, H.: The tempotron: a neuron that learns spike timing-based decisions. Nature Neuroscience 9(3), 420–428 (2006)CrossRefGoogle Scholar
  2. 2.
    Kasiński, A., Ponulak, F.: Comparison of supervised learning methods for spike time coding in spiking neural networks. International Journal of Applied Mathematics and Computer Science 16(1), 101–113 (2006)MathSciNetGoogle Scholar
  3. 3.
    Ponulak, F.: ReSuMe — new supervised learning method for the spiking neural networks. Technical report, Institute of Control and Information Engineering, Poznań University of Technology, Poland (2005)Google Scholar
  4. 4.
    Kasiński, A., Ponulak, F.: Experimental demonstration of learning properties of a new supervised learning method for the spiking neural networks. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696. Springer, Heidelberg (2005)Google Scholar
  5. 5.
    Ponulak, F.: Supervised learning in spiking neural networks with ReSuMe method. PhD thesis, Poznań University of Technology, Poland (2006)Google Scholar
  6. 6.
    Bohte, S.M.: The evidence for neural information processing with precise spike-times: A survey. Natural Computing 3(2), 195–206 (2004)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Ponulak, F., Kasiński, A.: Generalization properties of SNN trained with ReSuMe. In: Proceedings of the European Symposium on Artificial Neural Networks, ESANN 2006, Bruges, Belgium (2006)Google Scholar
  8. 8.
    Ponulak, F.: ReSuMe — proof of convergence. Technical report, Institute of Control and Information Engineering, Poznań University of Technology, Poland (2006)Google Scholar
  9. 9.
    Ponulak, F.: Analysis of ReSuMe learning process for spiking neural networks. International Journal of Applied Mathematics and Computer Science (in press)Google Scholar
  10. 10.
    Gerstner, W., Kistler, W.M.: Spiking neuron models. Cambridge University Press, Cambridge (2002)zbMATHGoogle Scholar
  11. 11.
    Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007)Google Scholar
  12. 12.
    Maass, W., Joshi, P., Sontag, E.D.: Computational aspects of feedback in neural circuits. PLoS Computational Biology 3(1), e165 (2007)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Gütig, R., Sompolinsky, H.: Neural mechanisms of speech processing: time warp invariants in adaptive integration time. In: Cosyne 2008: Computational and Systems Neuroscience, p. 337 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Răzvan V. Florian
    • 1
    • 2
  1. 1.Center for Cognitive and Neural Studies (Coneural)Cluj-NapocaRomania
  2. 2.Department of Computer ScienceBabeş-Bolyai UniversityCluj-NapocaRomania

Personalised recommendations