Location visible to members
Happy to announce the next Machine Learning Meetup with Yoshua Bengio (http://www.iro.umontreal.ca/~bengioy/yoshua_en/index.html), Full Professor of the Department of Computer Science and Operations Research, (http://www.iro.umontreal.ca/?lang=en) head of the Machine Learning Laboratory (LISA (http://www.iro.umontreal.ca/%7Elisa/lab)), CIFAR (http://www.cifar.ca/) Program co-director of the CIFAR Neural Computation and Adaptive Perception program, Canada Research Chair (http://www.chairs.gc.ca/)in Statistical Learning Algorithms, and he also holds the NSERC (http://www.nserc.ca/)-Ubisoft (http://www.ubisoft.com/)industrial chair.
Deep Learning Theory
Although neural networks have long been considered lacking in theory and much remains to be done, theoretical evidence is mounting 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.
6.00: Welcome, pizzas, beers and networking (more to be confirmed soon)
6.30: Talk (more to be confirmed soon)