Building a Bridge Between Spiking and Artificial Neural Networks (original) (raw)

Abstract

Spiking neural networks (SNN) are a promising approach for the detection of patterns with a temporal component. However they provide more parameters than conventional artificial neural networks (ANN) which make them hard to handle. Many error-gradient-based approaches work with a time-to-first-spike code because the explicit calculation of a gradient in SNN is - due to the nature of spikes - very difficult. In this paper, we present the estimation of such an error-gradient based on the gain function of the neurons. This is done by interpreting spike trains as rate codes in a given time interval. This way a bridge is built between SNN and ANN. This bridge allows us to train the SNN with the well-known error back-propagation algorithm for ANN.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Kasinski, A., Ponulak, F.: Comparison of supervised learning methods for spike time coding in spiking neural networks. Int. J. of Applied Mathematics and Computer Science, University of Z.Gora 16, 101–113 (2006)
    Google Scholar
  2. Bohte, S.M., Poutre, H.L., Kok, J.N.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48, 17–37 (2002)
    Article MATH Google Scholar
  3. Belatreche, A., Maguire, M.M.L.P., Wu, Q.X.: A method for supervised learning of spiking neural networks. In: Proc. of IEEE Cybernatics Intelligence - Challenges and Advances, pp. 39–44. IEEE Computer Society Press, Los Alamitos (2003)
    Google Scholar
  4. Ruf, B., Schmitt, M.: Learning temporally encoded patterns in networks of spiking neurons. Neural Processing Letters 5, 9–18 (1997)
    Article Google Scholar
  5. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
    Article Google Scholar
  6. Gerstner, W., Kistler, W.: Spiking Neuron Models. Cambridge University Press, Cambridge (2002)
    MATH Google Scholar
  7. Marian, I.: A biologically inspired model of motor control of direction. Master’s thesis, Department of Computer Science, University College Dublin (2002)
    Google Scholar
  8. König, P., Engel, A.K., Singer, W.: Integrator or coincidence detector? the role of the cortical neuron revisited. Trends in Neuroscience 19, 130–137 (1996)
    Article Google Scholar
  9. Prechelt, L.: Proben1 - a set of neural network benchmark problems and benchmarking rules. Technical report, Fakultät für Informatik, Universität Karlsruhe (1994)
    Google Scholar
  10. Riedmiller, M., Braun, H.: Rprop - a fast adaptive learning algorithm. Technical report, Fakultät für Informatik, Universität Karlsruhe (1992)
    Google Scholar
  11. Waibel, A., Hanazawa, T., Hilton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speach, and Signal Processing 37, 328–339 (1989)
    Article Google Scholar
  12. Wan, E.A.: Finite impulse response neural networks for autoregressive time series prediction. In: Weigend, A., Gershenfeld, N. (eds.) Proceedings of the NATO Advanced Workshop on Time Series Prediction and Analysis, Santa Fe, NM, May 14-17, 1993, Addison-Wesley, Reading (1993)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. University of Karlsruhe, CES – Chair for Embedded Systems, Karlsruhe, Germany
    Florian Kaiser & Fridtjof Feldbusch

Authors

  1. Florian Kaiser
  2. Fridtjof Feldbusch

Editor information

Joaquim Marques de Sá Luís A. Alexandre Włodzisław Duch Danilo Mandic

Rights and permissions

© 2007 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kaiser, F., Feldbusch, F. (2007). Building a Bridge Between Spiking and Artificial Neural Networks. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74690-4\_39

Download citation

Keywords

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.

Publish with us