[Lisa_seminaires] UdeM-McGill-MITACS machine learning seminar Tues, Nov. 24th

Guillaume Desjardins guillaume.desjardins at gmail.com
Dim 22 Nov 13:54:17 EST 2009


There is another MITACS talk this week, given by Karol Gregor from
NYU. Come one, come all !


Speaker: Karol Gregor, NYU
Title: Emergence of Complex-Like Cells in a Temporal Product Network
with Local Receptive Fields

Location: Pavillon André-Aisenstadt (Université de Montréal), room 3195
Time: November 24th 2009, 12h30-13h30

Abstract:
We introduce a new neural architecture and an unsupervised algorithm
for learning invariant representations from temporal sequence of
images. The system uses two groups of complex cells whose outputs are
combined multiplicatively: one that represents the content of the
image, constrained to be constant over several consecutive frames, and
one that represents the precise location of features, which is allowed
to vary over time.  The architecture uses an encoder to extract
features, and a decoder to reconstruct the input from the features.
The method was applied to patches extracted from consecutive movie
frames and produces orientation and frequency selective units
analogous to the complex cells in V1. An extension of the method was
used to train a network composed of units with local receptive field
spread over a large image of arbitrary size. Pooling over local
neighborhoods was also used which produces orientation-selective cells
that are organized in pinwheel patterns similar to those observed in
the mammalian visual cortex. By adding logistic regression classifier
applied to complex cell layer, the complete system becomes a very
fast, biologically inspired object recognition system - it contains
locally-connected simple and complex like cells, it can be applied to
full sized images, exhibits pinwheel patterns and has a feed-forward
encoder for efficient feature computation.

--
Guillaume Desjardins


Plus d'informations sur la liste de diffusion Lisa_seminaires