A very surprising shortcut
Instead of getting the correct probability distribution over
rivals by running a Markov chain until it reaches the
equilibrium distribution, use slight corruptions of the
data-vectors as the rivals (Bartlett’s experiments)
Learn by modifying the weights so as to lower the
energy of the true data and raise the energy of the
slightly corrupted data.
The learning stops when the model’s prejudices do not
corrupt the data in any systematic way.
Its OK if unlikely data-vectors are usually corrupted
into more likely ones.
This is exactly balanced by corrupting a small
fraction of the likely data-vectors into unlikely ones.