Pattern reconstruction with restricted Boltzmann machines
share
We show that the ability of a restricted Boltzmann machine to reconstruct a random pattern depends on the tail of the hidden prior distribution: hidden priors with strictly sub-Gaussian tails give only a logarithmic loss in pattern retrieval, while an efficient retrieval is much harder with hidden units with strictly super-Gaussian tails; reconstruction with sub-Gaussian hidden prior is regulated by the number of hidden units (as in the Hopfield model). This is proved by localisation estimates for the local minima of the energy function.
READ FULL TEXT