Abstract
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.
on research fellowship from : Laboratoire d’lnformatique et de Mécanique pour les Sciences de I’lngénieur / LIMSI BP.30 91406 Orsay cedex (France)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
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.
Fukushima, K.: A Hierarchical Neural Network Model for Selective Attention, Neural Computers. R.Eckmiller,C.v.d.Malsburg (Eds), Springer Verlag, 1988.
Rosenblatt, F.: The Perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review, Vol.65, pp 386–407, 1958.F
Béroule, D.: Un modele de mémoire adaptative, dynamique et associative pour le traitement automatique de la parole, These 3eme cycle, Orsay, 1985.
Leboeuf, J., BĂ©roule, D.:Processing of noisy patterns with a connectionnist system using a topographic representation of speech, Conference on Speech Technology, Edinburgh, 1987.
BĂ©roule, D. An introduction to the Adaptive, Dynamic and Associative Memory model ADAM, Neural Computing Architectures. I.Aleksander (Ed), MIT press & Kogan Page, June 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
BĂ©roule, D. (1989). The Never-Ending Learning. In: Eckmiller, R., v.d. Malsburg, C. (eds) Neural Computers. Springer Study Edition, vol 41. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83740-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-83740-1_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-50892-2
Online ISBN: 978-3-642-83740-1
eBook Packages: Springer Book Archive