[Lisa_seminaires] REMINDER: UdeM-McGill-MITACS machine learning seminar Tues Feb. 19, 10:00am, PAA 3195

Hugo Larochelle larocheh at iro.umontreal.ca
Lun 18 Fév 10:52:56 EST 2008


This week's seminar (see http://www.iro.umontreal.ca/article.php3? 
id_article=107&lang=en):


Modelling Image Patches With
A Directed Hierarchy Of Markov Random Fields


by Simon Osindero,
Department of Computer Science
University of Toronto

Location: Pavillon André-Aisenstadt (UdeM), room 3195
Time: February 19th 2008, 10:00am

I will describe an efficient learning procedure for a type of
multilayer generative model that combines the best aspects of Markov
Random Fields (MRFs) and deep, directed belief nets (DBNs). In
particular, I will consider hierarchies in which each hidden layer
has its own MRF whose energy function is modulated by the top-down
directed connections from the layer above.

Our proposed algorithm allows these generative models to be learned
one layer at a time, and when learning is complete we are able to use
a fast and simple inference procedure for computing a good
approximation to the posterior distribution on all of the hidden layers.

I will present preliminary results of our approach applied to an
image-patch dataset, and will show that this type of model is good at
capturing the statistics of patches of natural scenes. This is joint
work with Geoff Hinton.


Plus d'informations sur la liste de diffusion Lisa_seminaires