Storage capacity of a Potts-perceptron
Open Access
- 1 August 1991
- journal article
- Published by EDP Sciences in Journal de Physique I
- Vol. 1 (8) , 1109-1121
- https://doi.org/10.1051/jp1:1991104
Abstract
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 1Keywords
This publication has 0 references indexed in Scilit: