Track 1: Deep Learning Summit
Montreal

“Today’s models can be trained on huge quantities of data, but that’s not enough,” says Bengio, who together with LeCun and Google’s Geoffrey Hinton is one of the original musketeers of deep learning. “We need to discover learning algorithms that can take better advantage of all this unlabeled data that’s sitting out there.”

Yann LeCun once built an AI chip called ANNA. But he was 25 years ahead of his time. He and several other researchers designed this chip to run deep neural networks—complex mathematical systems that can learn tasks on their own by analyzing vast amounts of data—but ANNA never reached the mass market.

There are some estimates that five percent of all AI talent within the private sector are currently employed by Google. Perhaps no one among that rich talent pool has as deep a set of perspectives as Geoff Hinton. He has been involved in AI research since the early 1970s, which means he got involved before the field was really defined.

Researchers have developed a machine learning algorithm that can turn audio clips into realistic, lip-synced videos. A video shows former US president Barack Obama apparently speaking on a number of subjects including terrorism, though the clips were artificially generated using existing video addresses.

Computer scientists from the University of Toronto have created a software program that helps users avoid fashion faux pas. Raquel Urtasun and Sanja Fidler, along with colleagues in Spain, designed an algorithm that analyzes a person’s photograph to determine whether the wearer’s outfit is stylish. It also suggests ways to improve the ensemble and the subject’s overall appeal.

"A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data". In this paper Hugo Larochelle explores how to successfully apply and extend DocNADE to multimodal data, such as simultaneous image classification and annotation.