[Lisa_seminaires] Fwd: (reminder / change of room) UdeM-McGill Machine Learning Seminar: Geoffrey Hinton - Thurs, 17th @1500, AA1355

Guillaume Desjardins guillaume.desjardins at gmail.com
Mer 16 Mai 15:53:04 EDT 2012


This is a reminder for tomorrow's talk by Geoff Hinton. *Please note the
change of room*. The talk will now take place in pavillon Andre-Aisenstadt,
room 1355 (which should accomodate more people).

---------- Forwarded message ----------
From: Guillaume Desjardins <guillaume.desjardins at gmail.com>
Date: Mon, May 14, 2012 at 2:32 PM
Subject: UdeM-McGill Machine Learning Seminar: Geoffrey Hinton - Thurs,
17th @1500
To: "lisa_seminaires at iro.umontreal.ca" <lisa_seminaires at iro.umontreal.ca>


I am pleased to announce this upcoming talk by none other than Geoffrey
Hinton, entitled "Does the brain do inverse graphics?". The talk will take
place at the Universite de Montreal, pavillon Andre-Aisenstadt, room 5340,
this Thursday, May 17th from 15:00-16:00.

Hope to see you there!

Title: Does the brain do inverse graphics?

Abstract:
---------
Recognizing a familiar shape from the pattern of light intensities on the
retina is difficult because changes in viewpoint can dramatically change
the pattern of light intensities. The general belief among both
neuroscientists and neural network modelers is that the infero-temporal
pathway copes with viewpoint variation by using multiple levels of
representation in which each level is slightly more viewpoint-invariant
than the level below. Unfortunately, this approach cannot explain how we
can be acutely sensitive to the precise spatial relationships between
high-level parts such as a nose and a mouth.

>From an engineering perspective, the natural way to deal with spatial
relationships is to associate a vector of pose parameters with each
recognized part and to make use of the fact that spatial relationships can
then be modeled very efficiently using linear operations. This is what is
done in computer graphics and it is the reason why computer graphics can
deal with changes in viewpoint so easily. Despite the long history of
generative models of perception, computational neuroscientists have not
taken this aspect of computer graphics seriously, possibly because they do
not believe that the brain can do linear algebra. I shall show how a neural
net can learn to extract parts with explicit pose parameters from an image
and how this makes it very easy to recognize spatial configurations of
parts under a very wide range of viewpoints. I shall then sketch a way in
which the brain could use spike timing to implement the required linear
algebra very efficiently.

About the speaker:

Geoffrey Hinton designs machine learning algorithms. His aim is to discover
a learning procedure that is efficient at finding complex structure in
large, high-dimensional datasets and to show that this is how the brain
learns to see. His contributions include back-propagation, Boltzmann
machines, distributed representations, mixtures of experts, variational
learning, and deep belief nets. His current research uses local .capsules..
composed of a few hundred neurons that perform complicated internal
computations on their inputs and encapsulate the results into a small
vector of highly informative outputs that reveal the hidden structure in
the data.
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: https://webmail.iro.umontreal.ca/mailman/private/lisa_seminaires/attachments/20120516/7ba4f6e2/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires