Neuro-biological bases for spatio-temporal data coding in artificial neural networks

  • Gilles Vaucher
Poster Presentations 2 Neurobiology III: Single Cell/Learning Rules
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112)


Taking as a starting point Wilfrid Rall's dendritic tree model, well known by neuro-biologists, we propose a spatio-temporal data coding to introduce time in an artificial neuron (AN). This paper describes the biological origin of the coding and its links with the AN. With this type of coding, the algebraic properties of ANs are maintained and applied to sequence processing.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chappelier, J.-C., Grumbach, A.: Time in Neural Networks. SIGART Bulletin 5:3 (1994) 3–11Google Scholar
  2. 2.
    Mozayyani, N., Alanou, V., Dreyfus, J.-F., Vaucher, G.: A spatio-temporal data-coding applied to Kohonen maps. ICANN 2 (1995) 75–79Google Scholar
  3. 3.
    Reiss, M., Taylor, J.G.: Storing Temporal Sequences. Neural Networks 4 (1991) 773–787Google Scholar
  4. 4.
    Grossberg, S.: Contour enhancement, short term memory, and constancies in reverberating neural networks. Studies in Applied Mathematics 52 (1973) 217–257Google Scholar
  5. 5.
    Rall, W.: Core conductor theory and cable properties. Handbook of Physiology: The Nervous System 1 (1977) 39–97Google Scholar
  6. 6.
    Roché, E., Vaucher, G.: Perceptron Multi-Couches Étendu aux Corps des Complexes. Valgo 94-2 (1994) 23–37Google Scholar
  7. 7.
    Vaucher, G.: Un modèle de neurone artificiel conçu pour l'apprentissage non-supervisé de séquences d'événements asynchrones. Valgo 93-1 (1993) 66–107Google Scholar
  8. 8.
    Vaucher, G.: Study of a Self-Learning Artificial Neuron Model. ICANN (1993) 204Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Gilles Vaucher
    • 1
  1. 1.SUPÉLECCesson-Sévigné CedexFrance

Personalised recommendations