Storage capacity of a Potts-perceptron

Jean-Pierre Nadal , Albrecht Rau

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.

Domaines: Articles anciens

Jean-Pierre Nadal, Albrecht Rau. Storage capacity of a Potts-perceptron. Journal de Physique I, 1991, 1 (8), pp.1109-1121. ⟨10.1051/jp1:1991104⟩. ⟨jpa-00246396⟩