Does the Wake-Sleep Algorithm Produce Good
Density Estimators?
Brendan Frey Geoff Hinton Peter Dayan
In NIPS 8, 661-667.
Abstract
The wake-sleep algorithm (Hinton et al, 1995) is a relatively
efficient method of fitting a multilayer stochastic generative
model to high-dimensional data. In addition to the top-down connections
in the generative model, it makes use of bottom-up connections for
approximating the probability distribution over the hidden units given
the data, and it trains these bottom-up connections using a simple delta
rule. We use a variety of synthetic and real data sets to compare the
performance of the wake-sleep algorithm with Monte Carlo and mean field
methods for fitting the same generative model and also compare it with
other models that are less powerful but easier to fit.
compressed postscript pdf