Grande conference rcm2
ncm2 Distinguished Lecture
Monday, October 23/Le lundi 23 octobre 2000
"Training Products of Experts by Maximizing Contrastive Likelihood"
Geoffrey Hinton
Gatsby Computational Neuroscience Unit
University College London
It is possible to combine multiple probabilistic models of the same data by
multiplying the probabilities together and then renormalizing. This is a
very efficient way to model data which simultaneously satisfies many different
constraints. Each individual model can focus on giving high probability to
data vectors that satisfy just one of the constraints. Data vectors that satisfy
this one constraint but violate other constraints will be ruled out by their
low probability under the other models. For example, one model can generate
images that have the approximate overall shape of the digit 2 and other more local
models can ensure that local image patches contain segments of stroke with
the correct fine structure. Or one model of a word string can ensure that the
tenses agree and another can ensure that the number agrees.
Training a product of models appears difficult because, in addition to
maximizing the probabilities that the individual models assign to the
observed data, it is necessary to minimize the normalization term by making them
disagree on unobserved data. Fortunately, there is an efficient way to train a
product of models. Some examples of product models trained in this way will be
described, and I will show that they extract interesting structure from
images.
For information/pour tous renseignements:
rcm2@crm.umontreal.ca