Stability-capacity diagram of a neural network with Ising bonds

Abstract

The stability-capacity diagram of a fully connected neural network, whose bonds take the values 1 and -1 with equal probability, is determined numerically. Two different optimization methods (simulated annealing and tabu search) are used and their relevant features are discussed. The results indicate the existence of a region, in the stability-capacity plane, where replica-symmetry should be broken, within the replica-symmetric phase found by previous, analytical, computations. The critical capacity, consistent with simple arguments on information storage, is found to be less than one.