Statistical mechanics is applied to estimate the maximal information capacity per synapse (αc) of a multilayered feedforward neural network, functioning as a parity machine. For a large number of hidden units, K, the replica-symmetric solution overestimates dramatically the capacity, αc{∝}K². However, a one-step replica-symmetry breaking gives αc{~}lnK/ln2, which coincides with a theoretical upper bound. It is suggested that this asymptotic behavior is exact. Results for finite K are also discussed.
No takes yet. Share an insight, caveat, or question.
Barkai et al. (1990) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: