Université de Montréal

Deep learning

Gradient-based learning applied to document recognition

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate networ...

Issues and challenges facing rechargeable lithium batteries

Hybrid functionals based on a screened Coulomb potential

Hybrid density functionals are very successful in describing a wide range of molecular properties accurately. In large molecules and solids, however, calculating the exact (Hart...

Neural Machine Translation by Jointly Learning to Align and Translate

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at...

Teleporting an unknown quantum state via dual classical and Einstein-Podolsky-Rosen channels

An unknown quantum state \ensuremath{\Vert}\ensuremath{\varphi}〉 can be disassembled into, then later reconstructed from, purely classical information and purely nonclassical Ei...

Understanding the difficulty of training deep feedforward neural networks

Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with...

Representation Learning: A Review and New Perspectives

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more...

Generative adversarial networks

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a c...

Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC