 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| • |
If there are
more than a few hidden units, we cannot
|
|
|
compute the
normalizing term (the partition function)
|
|
|
because it has
exponentially many terms.
|
|
|
| • |
So use Markov
Chain Monte Carlo to get samples from
|
|
|
the model:
|
|
|
|
– |
Start
at a random global configuration
|
|
|
|
– |
Keep
picking units at random and allowing them to
|
|
|
stochastically
update their states based on their
|
|
|
energy
gaps.
|
|
|
|
– |
Use
simulated annealing to reduce the time required
|
|
to
approach thermal equilibrium.
|
|
|
| • |
At thermal
equilibrium, the probability of a
global
|
|
|
configuration is
given by the Boltzmann distribution.
|
|