[Lisa_seminaires] Fwd: [Stats] McGill Statistics Seminar Series - THIS FRIDAY

Yoshua Bengio yoshua.umontreal at gmail.com
Mer 16 Nov 08:33:25 EST 2016


---------- Forwarded message ----------
From: Yi Yang <yi.yang6 at mcgill.ca>
Date: 2016-11-15 11:14 GMT-05:00
Subject: [Stats] McGill Statistics Seminar Series - THIS FRIDAY
To: stats.students at math.mcgill.ca, stats at math.mcgill.ca, EBOH Secretary <
secretary.eboh at mcgill.ca>, "Jackie Castreje, Ms." <jackie.castreje at mcgill.ca>,
Yoshua Bengio <yoshua.umontreal at gmail.com>


*McGill Statistics Seminar Series*

Friday, *November 18* 2016, 15:30 – 16:30

Room 1205, Burnside Hall, 805 Sherbrooke West

______________________________________________________

*       Progress in Theoretical Understanding of Deep Learning*

Yoshua Bengio, PhD

Professor, University of Montreal



Deep learning has arisen around 2006 as a renewal of neural networks
research allowing such models to have more layers. Theoretical
investigations have shown that functions obtained as deep compositions of
simpler functions (which includes both deep and recurrent nets) can express
highly varying functions (with many ups and downs and different input
regions that can be distinguished) much more efficiently (with fewer
parameters) than otherwise, under a prior which seems to work well for
artificial intelligence tasks. Empirical work in a variety of applications
has demonstrated that, when well trained, such deep architectures can be
highly successful, remarkably breaking through previous state-of-the-art in
many areas, including speech recognition, object recognition, language
models, machine translation and transfer learning. Although neural networks
have long been considered lacking in theory and much remains to be done,
theoretical advances have been made and will be discussed, to support
distributed representations, depth of representation, the non-convexity of
the training objective, and the probabilistic interpretation of learning
algorithms (especially of the auto-encoder type, which were lacking one).
The talk will focus on the intuitions behind these theoretical results.






Organized by the McGill Statistics Group.



Seminar website: http://www.math.mcgill.ca/node/5358
--
Yi Yang
Assistant Professor of Statistics
Department of Mathematics and Statistics
McGill University
http://www.math.mcgill.ca/yyang/
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20161116/ed0188dc/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires