{"id":102,"date":"2017-06-01T08:21:54","date_gmt":"2017-06-01T08:21:54","guid":{"rendered":"http:\/\/bskog.com\/ai\/?p=102"},"modified":"2017-06-01T08:21:54","modified_gmt":"2017-06-01T08:21:54","slug":"deep-learning-school","status":"publish","type":"post","link":"http:\/\/bskog.com\/ai\/2017\/06\/01\/deep-learning-school\/","title":{"rendered":"Deep Learning School"},"content":{"rendered":"

Here you can watch lectures from the 2016 Deep Learning Summer School<\/a>\u00a0in Montreal.<\/p>\n

Course excerpt:<\/p>\n

Deep neural networks that learn to represent data in multiple layers of increasing abstraction have dramatically improved the state-of-the-art for speech recognition, object recognition, object detection, predicting the activity of drug molecules, and many other tasks. Deep learning discovers intricate structure in large datasets by building distributed representations, either via supervised, unsupervised or reinforcement learning.<\/p>\n

The Deep Learning Summer School 2016<\/a> is aimed at graduate students and industrial engineers and researchers who already have some basic knowledge of machine learning (and possibly but not necessarily of deep learning) and wish to learn more about this rapidly growing field of research.<\/p>\n

 <\/p>\n

 <\/p>\n

Here<\/a> is the schedule in which you could view the presentations<\/p>\n

table.schedule td {
vertical-align: top;
padding: 10px;
}<\/p>\n\n\n\n\n\n\n\n\n\n\n\n
\u00a001\/08\/2016<\/td>\n\u00a002\/08\/2016<\/td>\n\u00a003\/08\/2016<\/td>\n\u00a004\/08\/2016<\/td>\n\u00a005\/08\/2016<\/td>\n\u00a006\/08\/2016<\/td>\n\u00a007\/08\/2016<\/td>\n<\/tr>\n
9:00
\n10:30<\/td>\n		\n
Doina
\nPrecup<\/strong><\/div>\n
\n
Rob<\/strong><\/div>\n
\n
Yoshua<\/strong><\/div>\n
Bengio<\/strong><\/div>\n
Kyunghyun<\/strong><\/p>\n\n
Joelle<\/strong><\/div>\n
\n
Ruslan<\/strong><\/div>\n
\n
Bruno<\/strong><\/div>\n
10:30
\n11:00<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n<\/tr>\n
11:00
\n12:30<\/td>\n		\n
Hugo Larochelle<\/strong><\/div>\n
\n
Antonio Torralba<\/strong><\/div>\n
\n\n
Edward Grefenstette<\/strong><\/div>\n
\n
Pieter
\nAbbeel<\/strong><\/div>\n
\nSurya
\nGanguli<\/strong><\/p>\n
12:30
\n14:30<\/td>\n		Lunch<\/td>\nLunch<\/td>\nLunchWiDL event<\/a><\/td>\nLunch<\/td>\nLunch<\/td>\nLunch<\/td>\nLunch<\/td>\n<\/tr>\n
14:30
\n16:00<\/td>\n		\n
Hugo Larochelle<\/strong><\/div>\n
Alex Wiltschko<\/strong>
\nTorch I<\/em><\/a><\/td>\n		\nJulie Bernauer
\n(NVIDIA)
\n<\/strong>GPU programming with CUDA<\/em><\/a><\/td>\n		Joelle, Pieter & Doina
\n<\/strong>Advanced Topics in RL<\/em><\/a><\/td>\n		Contributed
\ntalks<\/strong>
\nSession 4<\/td>\n		Contributed
\ntalks<\/strong>
\nSession 4<\/td>\n<\/tr>\n
16:00
\n16:30<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n		Coffee
\nBreak<\/td>\n<\/tr>\n
16:30
\n18:00<\/td>\n		Pascal
\nLamblin<\/strong><\/p>\n		Practical
\nSession
\n<\/strong>\u00a0Alex Wiltschko
\n<\/strong>(Torch)<\/em>
\n<\/strong><\/p>\n
<\/div>\n

Fr\u00e9d\u00e9ric Bastien<\/strong>
\n(Theano)<\/em><\/td>\n

Jeff
\nDean<\/strong><\/p>\n		Contributed
\ntalks<\/strong>
\nSession 1<\/td>\n		Contributed
\ntalks<\/strong>
\nSession 2<\/td>\n		Contributed
\nPosters<\/strong>
\nSession 1<\/td>\n		Contributed
\nPosters<\/strong>
\nSession 2<\/td>\n<\/tr>\n
\u00a0Evening<\/td>\nOpening Reception<\/a>
\n(18:00-20:30)
\n— by —
\nImagia<\/a><\/em><\/td>\n		\u00a0Happy Hour<\/a>
\n(18:45-22:30)
\nbuses at 18:30
\n— by —
\nMaluuba<\/a><\/em><\/td>\n		Happy Hour<\/a>
\n(18:30-20:30)
\n— by —
\nCreative Destruction Lab<\/a> <\/em><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n

(or you can just follow them in consecutive order at http:\/\/videolectures.net\/deeplearning2016_montreal\/<\/a> since they seem to be in the order they were presented.)<\/p>\n

Contributed talks:<\/h3>\n

12:55 Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks<\/a>
\nRajarshi Das<\/p>\n

14:29 Professor Forcing: A New Algorithm for Training Recurrent Networks<\/a>
\nAnirudh Goyal<\/p>\n

10:59 Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations<\/a>
\nTegan Maharaj<\/p>\n

18:58 Deep multi-view representation learning of brain responses to natural stimuli<\/a>
\nLeila Wehbe<\/p>\n

14:49 Learning to Communicate with Deep Multi\u00ad-Agent Reinforcement Learning<\/a>
\nJakob Foerster<\/p>\n

13:57 Model-Based Relative Entropy Stochastic Search<\/a>
\nAbbas Abdolmaleki<\/p>\n

16:33 Learning Nash Equilibrium for General-Sum Markov Games from Batch Dat<\/a>
\nJulien Pe\u0301rolat<\/p>\n

20:30 A Network-based End-to-End Trainable Task-oriented Dialogue System<\/a>
\nTsung-Hsien Wen<\/p>\n

15:28 Inference Learning<\/a>
\nPatrick Putzky<\/p>\n

16:45 Variational Autoencoders with PixelCNN Decoders<\/a>
\nIshaan Gulrajani<\/p>\n

13:33 An Infinite Restricted Boltzmann Machine<\/a>
\nMarc-Alexandre C\u00f4t\u00e9<\/p>\n

15:15 Deep siamese neural network for prediction of long-range interactions in chromatin<\/a>
\nDavide Chicco<\/p>\n

14:09 Beam Search Message Passing in Bidirectional RNNs: Applications to Fill-in-the-Blank Image Captioning<\/a>
\nQing Sun<\/p>\n

18:40 Analyzing the Behavior of Deep Visual Question Answering Models<\/a>
\nAishwarya Agrawal<\/p>\n

13:55 Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation<\/a>
\nSina Honari<\/p>\n","protected":false},"excerpt":{"rendered":"

Here you can watch lectures from the 2016 Deep Learning Summer School\u00a0in Montreal. Course excerpt: Deep neural networks that learn to represent data in multiple layers of increasing abstraction have dramatically improved the state-of-the-art for speech recognition, object recognition, object detection, predicting the activity of drug molecules, and many other tasks. Deep learning discovers intricate … <\/p>\n

Continue reading “Deep Learning School”<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9,11,16],"tags":[],"class_list":["post-102","post","type-post","status-publish","format-standard","hentry","category-courses","category-deep-learning","category-learning-material"],"_links":{"self":[{"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/posts\/102","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/comments?post=102"}],"version-history":[{"count":0,"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/posts\/102\/revisions"}],"wp:attachment":[{"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/media?parent=102"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/categories?post=102"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/bskog.com\/ai\/wp-json\/wp\/v2\/tags?post=102"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}