Unsupervised Learning of Temporal Sequences by Neural Networks

  • B. Gas
  • R. Natowicz
Conference paper


We propose to define a new model of formal neural network. This model extends existing Hopfield networks to process temporal data and achieve a non-supervised learning of them. We propose a learning law to adress in this context the sensitivity to input changes. A spatial representation of network’s temporal activity is given by which learnt sequences can be identified. An example of such a network is given and the results of the simulation are presented.


Input Sequence Spike Train Temporal Sequence Spatial Representation Network Cell 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    B. Gas, R. Natowicz. A model of formal neural networks for unsupervised learning of binary temporal sequences. IJCNN, Baltimore (1992).Google Scholar
  2. [2]
    B. Gas. Un modèle connexionniste non supervisé pour l’apprentissage et la reconnaissance de séquences tem-porelles. PhD thesis, Université de Paris X I (1994).Google Scholar
  3. [3]
    B. Changeux. L’Homme Neuronal. Fayard 106, 110 (1983).Google Scholar
  4. [4]
    J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities Proc. Nat. Acad. Sci. USA, vol. 79, pp. 2554–2558 (1982).MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • B. Gas
    • 1
  • R. Natowicz
    • 2
  1. 1.ENSEA-ETISCergy-Pontoise cedexFrance
  2. 2.ESIEENoisy-Le-GrandFrance

Personalised recommendations