Experts in: Machine learning
BENGIO, Yoshua
Professeur titulaire
- Machine learning
- Representation learning
- Deep learning
- Temporal database
- Artificial intelligence
- Probabilistic models
- Statistical models
- Neural Networks
- Computer vision
- Data science
- Natural-language processing (NLP)
- COVID-19
- COVID19
My long-term goal is to understand intelligence; understanding its underlying principles would give us access to artificial intelligence (AI), and I believe that learning algorithms are essential in this quest. Learning algorithms could give computers the ability to capture operational knowledge (not necessarily in symbolic / verbal form) from examples.
CHARLIN, Laurent
Professeur associé
COURVILLE, Aaron
Professeur agrégé
ECK, Douglas
Professeur associé
Douglas Eck, research scientist and lead for Google Brain's Magenta project, is teaching computers how to generate their own music, video, images, and text using neural networks and other types of machine learning.
GENDREAU, Michel
Professeur associé
- Operations research
- Transports
- Transportation networks
- Metaheuristic
- Optimization of transport systems
- Stochastic optimization
- Machine learning
- Logistics
My main research area is the application of operations research to transportation and telecommunication planning. A large portion of my work deals with the development of efficient metaheuristics for solving difficult problems in this area. As co-director of the Laboratory on Intelligent Transportation Systems of the Centre for Research on Transportation, I am also very interested in all real-time transportation planning problems.
LACOSTE-JULIEN, Simon
Professeur agrégé
MEMISEVIC, Roland
Professeur associé
- Machine learning
- Representation learning
- Deep learning
- Visual features extraction
- Bio-inspired computing
- Neural Networks
- Computer vision
- Artificial intelligence
- Algorithmics
- Statistical learning
My research interests are in machine learning and computer vision. I develop algorithms that extract information from large amounts of data, with a particular focus on the extraction of spatial and spatio-temporal features from images and videos. I am also interested in the development of deep learning architectures and bio-inspired models and their applications in automatic data analysis.
MITLIAGKAS, Ioannis
Professeur adjoint
PAL, Christopher
Professeur associé
POTVIN, Jean-Yves
Professeur titulaire, Directeur adjoint
- Genetic algorithm
- Logistics
- Metaheuristic
- Vehicle routing problem
- Tabu search
- Transports
- Combinatorial optimization
- Communication protocol
- Network design
- Machine learning
- Parallel computing
- Artificial intelligence
My research interests focus on the development of metaheuristics, such as tabu search and genetic algorithms, for solving discrete optimization problems in the transportation domain. I am particularly interested in vehicle routing problems with different side constraints, like service time windows at customer locations. These problems can model many real-world applications such as distribution of goods by commercial vehicles, courier services, para-transit services, etc. I also study dynamic variants of these problems when customer requests dynamically occur over time and must be integrated in real-time into the current routes.
RABUSSEAU, Guillaume
Professeur adjoint
VINCENT, Pascal
Professeur agrégé
- Machine learning
- Representation learning
- Deep learning
- Artificial intelligence
- Big data
- Statistical models
- Pattern recognition
- Neural Networks
- Algorithmics
My research interests are centered around discovering fundamental computational principles that underlie the extraordinary capabilities to learn from the environment, understand it and adapt to it that characterize intelligence. The development of novel machine learning algorithms based on such principles, and trained on very large data sets, is at the heart of the latest technological breakthroughs in artificial intelligence.
More specifically, I research how higher level representations that carry meaning can be constructed autonomously, starting from streams of raw sensory input (such as images and sounds). Similarly to what our brain's neural networks naturally know how to do, this amounts to intelligently modeling the structure of the observed reality, by discovering and exploiting hidden and complex statistical regularities that it follows.