A picture of a conditional,
 higher-order Boltzmann machine
(Hinton & Lang,1985)
object-based
features
viewing
transform
We can view it as a
Boltzmann machine in
which the inputs create
interactions between the
other variables.
This type of model is
now called a conditional
random field.
It is hard to learn with
two hidden groups.
retina-
based
features