Recurrent sampling models for the
Helmholtz machine.
Peter Dayan
Neural Computation, 11, 653-677.
Abstract
Many recent analysis-by-synthesis density estimation models of
cortical learning and processing have made the crucial simplifying
assumption that units within a single layer are mutually independent
given the states of units in the layer below or the layer above. In
this paper, we suggest using either a Markov random field or an
alternative stochastic sampling architecture to capture explicitly
particular forms of dependence within each layer. We develop the
architecture in the context of real and binary Helmholtz machines.
Recurrent sampling can be used to capture correlations within layers
in the generative or the recognition models, and we also show how
these can be combined.
compressed postscript   pdf