The Never-Ending Learning
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.
KeywordsElementary Signal Cross Flow Incoming Flow Incoming Signal Neural Computer
Unable to display preview. Download preview PDF.
- 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.Fukushima, K.: A Hierarchical Neural Network Model for Selective Attention, Neural Computers. R.Eckmiller,C.v.d.Malsburg (Eds), Springer Verlag, 1988.Google Scholar
- 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.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.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