The Never-Ending Learning

  • Dominique Béroule
Conference paper
Part of the Springer Study Edition book series (volume 41)


A processing principle supported by a dynamic memory is presented, which makes learning involved in the overall treatment. By emphasizing the operational constraints of this principle, and taking into account the concrete tasks to be performed, a modular and parallel architecture is gradually defined. It is shown that this architecture arises in the course of processing, through two complementary mechanisms: the long-term reinforcement or dissolution of memory pathways, and the episodic sprouting of new pathways. The resulting system basically detects coincidences between a cross flow of internal signals and an afferent flow of incoming signals.


Elementary Signal Cross Flow Incoming Flow Incoming Signal Neural Computer 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kohonen, T.: The role of Adaptative and Associative Circuits in Future Computer Designs, Neural Computers. R.Eckmiller,C.v.d.Malsburg (Eds), Springer Verlag, 1988.Google Scholar
  2. 2.
    Fukushima, K.: A Hierarchical Neural Network Model for Selective Attention, Neural Computers. R.Eckmiller,C.v.d.Malsburg (Eds), Springer Verlag, 1988.Google Scholar
  3. 3.
    Rosenblatt, F.: The Perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review, Vol.65, pp 386–407, 1958.FCrossRefMathSciNetGoogle Scholar
  4. 4.
    Béroule, D.: Un modele de mémoire adaptative, dynamique et associative pour le traitement automatique de la parole, These 3eme cycle, Orsay, 1985.Google Scholar
  5. 5.
    Leboeuf, J., Béroule, D.:Processing of noisy patterns with a connectionnist system using a topographic representation of speech, Conference on Speech Technology, Edinburgh, 1987.Google Scholar
  6. 6.
    Béroule, D. An introduction to the Adaptive, Dynamic and Associative Memory model ADAM, Neural Computing Architectures. I.Aleksander (Ed), MIT press & Kogan Page, June 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Dominique Béroule
    • 1
  1. 1.Instituut voor Perceptie Onderzoek / IPOEindhovenNederland

Personalised recommendations