Equilibriumandnon-Equilibriumregimesinthe learningofRestrictedBoltzmannMachines

Neural Information Processing Systems 

Inparticular,weshowthat using the popular k (persistent) contrastive divergence approaches, with k small, the dynamics of the learned model are extremely slow and often dominated by strong out-of-equilibrium effects.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found