Brendan J. Frey 1997.
Continuous sigmoidal belief networks trained using slice sampling.
In Advances in Neural Information Processing Systems 9.
MIT Press: Cambridge, MA. Presented at the
Neural Information Processing Systems Conference, Denver, Colorado,
Dec. 1996.
Real-valued random hidden variables can be useful for modelling
latent structure that explains correlations among observed
variables. I propose a simple unit that adds zero-mean Gaussian
noise to its input before passing it through a sigmoidal
squashing function. Such units can produce a variety of useful
behaviors, ranging from deterministic to binary stochastic to
continuous stochastic. I show how "slice sampling"
can be used for
inference and learning in top-down networks of these units and
demonstrate learning on two simple problems.
Compressed postscript,
uncompressed postscript.
Back to Brendan Frey's home page.