We study a two-layer neural network made of N and M(N) neurons, producing a
two-way association search for a family of p(N) patterns, where each patte
rn is a pair of two independent sub-categories of information having respec
tively N and M(N) components. In terms of the ratio gamma = lim(N --> infin
ity) M(N)/N, we study the retrieval capability of this network and show tha
t there exists, at least, three regimes of association for which we determi
ne the evolution of the threshold alpha (c)(gamma) of the storage capacity
alpha = lim(N) (--> infinity) p(N)/N.