Daniel Tarlow (Google Brain)

Marc G. Bellemare (Google Brain)

Nicolas Le Roux (Google Brain)

Timothy O'Donnell (Linguistics, McGill)

Machine Learning Algorithms and Applications for Smart Grid.

I work on reinforcement learning, AI safety

I work on visual reasoning, multimodal learning, metalearning and deep RL.

I employ the concepts in statistical physics, in particular polymer physics, in order to develop efficient exploration and learning algorithms in reinforcement learning.

I'm interested in deep reinforcement learning, particularly in the aspects related to generalization and how it is possible to integrate model-based and model-free learning.

I am interested in building meaningful models in NLP that can be used in a wide range of tasks using transfer learning techniques

I work on deep reinforcement learning

I work on multi-agent communication (emergent communication)

I am interested in safety related issues in hierarchical reinforcement learning.

Density models in deep RL for representation learning

I apply machine learning to analyse human physiological signals such as speech and cardiorespiratory activity.

I am currently exploring the theoretical connections between Weighted Automata and RNN

I'm interested in fundamental aspects of Deep Learning, as well as "RL-Deep", and currently working on unsupervised learning in RL domains.

I'm interested in deep reinforcement and imitation learning, especially the problem of transferring knowledge and skills between tasks.

I am interested in developing advanced machine learning techniques for biological sequence analysis and gene regulatory networks

I am interested in the very theoretical aspects of CS. Category theory allows us to think of CS in terms of the structures and to work in the mathematical world.

I am exploring strategies for model-based deep RL in atari games

I am interested in bandits and reinforcement learning with provable guarantees.

My research focus is on computational pragmatics and natural language generation. I am particularly interested in the application of deep learning to these problem domains.

I'm interested in exploration and temporal abstraction in deep RL.

I'm interested in Generative Modelling of structured data such as graphs and language. I'm also interested in Meta-Learning and Causality in these domains. In the past I've worked on Adversarial Machine Learning such as GAN's and adversarial attacks.

I am currently interested in privacy-preserving algorithms, reinforcement Learning and transfer Learning.

I’m interested in model free deep RL

I am broadly interested in understanding the latent space during the life-time of an agent in the perceptual domain. Currently my work focuses on designing reinforcement algorithms which are more interpretable in context of their behavior.

I work on reasoning for language understanding and language generation (dialog systems)

I am working on Text Mining and Authorship Analysis. My interest is in using Natural Language Processing, and Deep Learning techniques to enhance authorship attribution.

Working on improving Robot Navigation around people. Currently using Deep Learning and Inverse Reinforcement Learning.

Using uncertainty to drive exploration in reinforcement learning

I am interested in Privacy-Preserving Reinforcement Learning. I am also interested in adopting intuitions from statistical mechanics to develop exploration policies in Reinforcement Learning.

I work on deep reinforcement learning

Currently, my work focuses on integrating optimization methods in reinforcement learning to reduce computational costs and gain more robust models in industrial scale.

Causal, energy-based, deep models.

Natural language reasoning and generation

I work on temporal aspects in Reinforcement Learning. Specifically, I am interested in solving temporal credit assignment in reinforcement learning.

I am interested in goal oriented conversational agents.

I'm interested in representation learning and reasoning tasks for graph structured data.

I'm interested in policy optimization and efficient learning in deep RL

I use neural networks to build conversational agents. I've particularly investigated datasets for building dialogue systems, and how we should evaluate them.

Deep reinforcement learning for continuous control.

I focus mainly on reinforcement learning and some surrounding problems

Deep Learning and Reinforcement Learning in Medical Imaging

I'm trying to incorporate nonlinearity into WFA

Predictive knowledge, temporal abstraction and models in RL

I work on summarization and text simplification with deep learning and reinforcement learning techiniques

I work on the theoretical understanding of learning tasks involving sequential data.

I'm interested in the application of deep learning, transfer learning, generative models in medical imaging domain.

Development of a dataset and a model to perform the aggregation of entities in automatic summarization

Machine Learning applications (causal inference) to healthcare

Model Based RL, Probablistic Graphical Models

I investigate reinforcement learning as well as meta-learning.

Common sense

My current research focus are: integrating knowledge graph information into natural language reasoning task & dynamic construction of knowledge graph from text

Graph representation learning for anomaly detection, model based RL

Working on generative models for sensor data

I am working on temporal abstractions in Deep Reinforcement Learning. I am trying to bridge the gap between spectral graph theory and reinforcement learning.

I am working on text summarization in NLP

i work on Deep Reinforcement Learning and model based Reinforcement Learning.

I currently working on better understanding policy gradient methods in Reinforcement Learning

Learning and Entropy

I'm currently working on automation of seizure detection using Deep Learning.

I work on reinforcement learning

Anomaly Detection in Temporal graph / Continual Learning

Exploration, goal-conditioned/multi-goal RL

I am working to create Deep RL agent to play text-based games

I am working on deeping learning in Medical Physics

stochastic variance reduction methods for policy evaluation

I am currently interested in bandits and multi-agent reinforcement learning.

Name | Degree | Last Known Whereabouts |
---|---|---|

Pierre-Luc Bacon | Ph.D. 2018 | Assistant Professor at University of Montreal |

Audrey Durand | Postdoc. 2018- 2019 | Assistant Professor at University of Laval |

Guillaume Rabusseau | Postdoc. 2016- 2018 | Assistant Professor at University of Montreal |

Herke Van Hoof | Postdoc. 2016- 2018 | Assistant Professor at University of Amsterdam |

Negar Ghourchian | Ph.D. 2017 | Research Scientist at Aerial.ai |

Boyu Wang | Ph.D. 2016 | Postdoc at Princeton Neuroscience Institute |

Laurent Charlin | Postdoc 2015-2016 | Assistant Professor of statistics at HEC Montréal |

Lucas Lehnert | M.Sc. 2016 | Ph.D. student at Brown University |

Bénédicte Leonard-Cannon | M.Sc. 2016 | Software Engineer at Microsoft |

Gheorghe Comanici | Ph.D. 2016 | Software Engineer at Google Montreal |

Borja Balle | Postdoc 2013-2015 | Lecturer at Lancaster University |

Philip Bachman | Ph.D. 2015 | Researcher at Maluuba, Montreal |

Melanie Lyman-Abramovitch | M.Sc. 2015 | |

Andrew Sutcliffe | M.Sc. 2015 | |

Gabriel Forgues | M.Sc. 2015 | Software Engineer at Facebook Seattle |

Angus Leigh | M.Sc. 2015 | Software Engineer at Google X |

Nastaran Jafarpour | Ph.D. 2014 | Data Scientist at Via Science, Montreal |

Jinxu Jia | M.Sc. 2014 | Software Engineer at Microsoft Seattle |

Hiu Kim Yuen | M.Sc. 2014 | Software Engineer at LoopPulse, Hong Kong |

Yuri Grinberg | Ph.D. 2014 | National Research Council Canada |

Clement Gehring | M.Sc. 2014 | Ph.D. student at MIT |

Robert D. Vincent | Ph.D. 2014 | Teacher at Vanier College |

Hang Ma | M.Sc. 2014 | Ph.D. student at University of Southern California |

Mahdi Milani Fard | Ph.D. 2014 | Software Engineer at Google Mountain View |

Ouais Alsharif | M.Sc. 2014 | Software Engineer at Google Mountain View |

Will Hamilton | M.Sc. 2014 | Ph.D. student at Stanford University |

Amir-massoud Farahmand | Postdoc 2013 | Machine Learning Researcher at Mitsubishi Electric Research Laboratories |

Beomjoon Kim | M.Sc. 2013 | Ph.D. student at MIT |

Andre M.S. Barreto | Postdoc 2011-2013 | Research Scientist at Google Deepmind |

Athena K. Moghaddam | M.Sc. 2013 | Software Engineer at Facebook Menlo Park |

Sylvie C.W. Ong | Postdoc 2012-2013 | Software Engineer at Nuance Communications Montreal |

Guillaume Saulnier Comte | M.Sc. 2013 | Software Engineer at Google Seattle |

Danesh Ghafoorzadehnobar | M.Sc. 2013 | Software Engineer at Microsoft in Redmond, Washington |

Cosmin Paduraru | Ph.D. 2013 | Postdoctoral fellow in COSMO Lab |

Gheorghita Catalin Bordianu | M.Sc. 2012 | Software Engineer at 500px |

Jordan Frank | Ph.D. 2012 | Software Engineer at Facebook Seattle |

Pablo Samuel Castro | Ph.D. 2011 | Software Engineer at Google Montreal |

Amin Atrash | Ph.D. 2011 | Postdoc at the School of Computer Science at USC |

Shaowei Png | M.Sc. 2011 | Software Engineer in Google Seattle/Kirkland |

Susan Shortreed | Postdoc 2009-2011 | Assistant Scientific Investigator at Group Health Research Institute |

Keith Bush | Postdoc 2008-2010 | Assistant Professor of Computer Science, University of Arkansas at Little Rock |

Julien Villemure | M.Sc. 2010 | |

Arthur Guez | M.Sc. 2010 | Research Scientist at Google DeepMind |

Ryan Faulkner | M.Sc. 2010 | Research Scientist at Google DeepMind |

Robert Kaplow | M.Sc. 2010 | Software Engineer at Google Montreal |

Robert West | M.Sc. 2010 | Ph.D. student, Stanford University |

Monica Dinculescu | M.Sc. 2010 | Software Engineer at Google Mountain View |

Stéphane Ross | M.Sc. 2008 | Software Engineer at Google X |

Masoumeh Izadi | Ph.D. 2007 | R&D manager in sport analytics at Broadcast Solutions in Singapore |

Marc Bellemare | M.Sc. 2007 | Research Scientist at Google DeepMind |

Bohdana Ratitch | Ph.D. 2005 | Scientific Advisor at Quintiles |

Danielle Azar | Ph.D. 2004 | Lebanese American University |

Martin Stolle | M.Sc. 2003 | Software Engineer at Google Zurich |

Francois Rivest | M.Sc. 2002 | Assistant Professor at the Royal Military College of Canada |