Résumé. 2014 Nous considérons une famille de modèles qui généralise le modèle de Hopfield, et qui peut s’étudier de façon analogue. Cette famille englobe des schémas de type palimpseste, dont les propriétés s’apparentent à celles d’une mémoire de travail (mémoire à court terme). En utilisant la méthode des répliques, nous obtenons un formalisme simple qui permet une comparaison détaillée de divers schémas d’apprentissage, et l’étude d’effets variés, tel l’apprentissage par répétition. Abstract. 2014 We consider a family of models, which generalizes the Hopfield model of neural networks, and can be solved likewise. This family contains palimpsestic schemes, which give memories that behave in a similar way as a working (short-term) memory. The replica method leads to a simple formalism that allows for a detailed comparison between various schemes, and the study of various effects, such as repetitive learning.
[1]
Stanislas Dehaene,et al.
Networks of Formal Neurons and Memory Palimpsests
,
1986
.
[2]
S Dehaene,et al.
Spin glass model of learning by selection.
,
1986,
Proceedings of the National Academy of Sciences of the United States of America.
[3]
J J Hopfield,et al.
Neural networks and physical systems with emergent collective computational abilities.
,
1982,
Proceedings of the National Academy of Sciences of the United States of America.
[4]
Sompolinsky,et al.
Storing infinite numbers of patterns in a spin-glass model of neural networks.
,
1985,
Physical review letters.