A Model for Fast Analog Computations with Noisy Spiking Neurons

  • Wolfgang Maass

Abstract

We show that networks of spiking neurons can simulate arbitrary feedforward sigmoidal neural nets in a way which has previously not been considered. This new approach is based on temporal coding by single spikes (respectively by the timing of synchronous firing in pools of neurons), rather than on the traditional interpretation of analog variables in terms of firing rates.

As a consequence we can show that networks of noisy spiking neurons are “universal approximators” in the sense that they can approximate with regard to temporal coding any given continuous function of several variables.

Keywords

Activation Function Firing Rate Neural Information Processing System Dendritic Tree Firing Time 
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]
    Gerstner, W. and van Hemmen, J. L. (1994) How to describe neuronal activity: spikes, rates, or assemblies? Advances in Neural Information Processing Systems, vol. 6, Morgan Kaufmann (San Mateo) 463–470.Google Scholar
  2. [2]
    Hopfield, J. J. (1991) Olfactory computation and object perception. Proc. Nat. Ac. Sci. USA, vol. 88, 6462–6466.Google Scholar
  3. [3]
    Hopfield, J. J. (1995) Pattern recognition computation using action potential timing for stimulus representations. Nature, vol. 376, 33–36.Google Scholar
  4. [4]
    Leshno, M., Lin, V. Y., Pinkus, A., and Schocken, S. (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, vol. 6, 861–867.Google Scholar
  5. [5]
    Linsker, R. (1988) Self-organization in a perceptual network. Computer Magazine, vol. 21, 105–117.Google Scholar
  6. [6]
    Maass, W. (1995) Fast sigmoidal networks via noisy spiking neurons,to appear in Neural Computation.Google Scholar
  7. [7]
    Maass, W. (1996) On the computational power of noisy spiking neurons. Advances in Neural Information Processing Systems, vol. 8, MIT-Press (Cambridge), 211–217.Google Scholar
  8. [8]
    Mainen, Z.F. and Sejnowski, T. J. (1995) Reliability of spike timing in neocortical neurons. Science, vol. 268, 1503–1506.Google Scholar
  9. [9]
    Markram, H. and Sakmann, B. (1995) Action potentials propagating back into dendrites trigger changes in efficacy of single-axon synapses between layer V pyramidal neurons. Abstract 788.11 in Vol. 21 of the Proc. of the Conference of the Society for Neuroscience.Google Scholar
  10. [10]
    Mel, B. W. (1993) Synaptic integration in an excitable dendritic tree. J. of Neurophysiology, vol. 70, 1086–1101.Google Scholar
  11. [11]
    Rolls, E. T. (1994a) Brain mechanisms for invariant visual recognition and learning. Behavioural Processes, vol. 33, 113–138.Google Scholar
  12. [12]
    Rolls, E. T. and Tovee, M. J. (1994b) Processing speed in the cerebral cortex, and the neurophysiology of visual backward masking. Proc. Roy. Soc. B., vol. 257, 9–15.Google Scholar
  13. [13]
    Shepherd, G. M. (1994) Neurobiology,3rd ed. Oxford University Press (New York).Google Scholar
  14. [14]
    Thorpe, S. J. and Imbert, M. (1989) Biological constraints on connectionist modelling. In: Connectionism in Perspective, Pfeifer, R., Schreter, Z., Fogelman-Soulié, F., and Steels, L., eds., Elsevier (North-Holland).Google Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Wolfgang Maass
    • 1
  1. 1.Institute for Theoretical Computer ScienceTechnische Universitaet GrazGrazAustria

Personalised recommendations