LEARNING AND GENERALIZATION THEORIES OF LARGE COMMITTEE-MACHINES
Rémi Monasson, Riccardo Zecchina · Modern Physics Letters B · 1995
The study of the distribution of volumes associated to the internal representations of learning examples allows us to derive the critical learning capacity [Formula: see text] of large committee machines, to verify the stability of the solution in the limit of a large number K of hidden units and to find a Bayesian generalization cross-over at a=K.