Re:An Introduction to Probabilistic Graphical Models (2003) ...
by ganfortran on Wednesday March 29, 2017 @01:44AM
(#13983746)
Do they train with backpropagation efficiently?
[ Parent
| on HN ]
Re:An Introduction to Probabilistic Graphical Models (2003) ...
by twiecki on Wednesday March 29, 2017 @03:15AM
(#13984083)
No, back-propagation would not give full Bayesian inference (although there are some tricks [0]). They instead use variational inference[1], which allows for fast inference of continuous PGMs.