J. Phys. I France
Volume 1, Numéro 8, August 1991
Page(s) 1109 - 1121
DOI: 10.1051/jp1:1991104
J. Phys. I France 1 (1991) 1109-1121

Storage capacity of a Potts-perceptron

Jean-Pierre Nadal1 and Albrecht Rau2

1  Lab. de Physique Statistique, Ecole Normale Supérieure, 24 rue Lhomond, F-75231 Paris Cedex 05, France
2  Dept. of Theoretical Physics, University of Oxford, 1 Keble Rd., GB-Oxford OX1 3NP, G.B.

(Received 22 January 1991, accepted in final form 30 April 1991)

We consider the properties of "Potts" neural networks where each neuron can be in Q different states. For a "Potts-perceptron" with N Q-states input neurons and one Q' states output neutron, we compute the maximal storage capacity for unbiased patterns. In the large N limit the maximal number of patterns that can be stored is found to be proportional to N(Q-1)f(Q'), where f(Q') is of order 1.

© Les Editions de Physique 1991