Symmetry breaking in nonmonotonic neural networks

The optimal performance of a nonmonotonic neural network is studied by the replica method. In analogy to what happens in multi-layered networks, the authors show that replica symmetry breaking (RSB) is required. The distribution of the patterns stabilities, the correlations in the distribution of the internal representation and the optimal capacity per synapse ( alpha _c approximately=4.8) are computed with one step of RSB.