Aaron Courville
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2023
Aaron Courville is a Canada CIFAR AI Chair at Mila, a CIFAR fellow of the Learning in Machines and Brains program, and an associate professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal.
Courville is a computer scientist whose current research focuses on the development of deep learning models and methods. He is particularly interested in developing probabilistic models and novel inference methods. While he has mainly focused on applications to computer vision, he is also interested in other domains such as natural language processing, audio signal processing, speech understanding and just about any other artificial-intelligence-related task.
Awards
- Canada Research Chair in Learning Representations that Generalize Systematically, 2022
- Winning Team Member of the Transfer Learning Challenge, ICML Workshop, 2011
- Winning Team Member of the Unsupervised and Transfer Learning Challenge Phase II, NIPS, 2011
Relevant Publications
D'Oro, P., Schwarzer, M., Nikishin, E., Bacon, P., Bellemare, M., Courville A. (2023). Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier. ICLR.
Schwarzer, M., Obando-Ceron, J., Courville, A., Bellemare, M., Agarwal, R., Castro, P.S. (2023). Bigger, Better, Faster: Human-level Atari with human-level efficiency. ICML.
Nikishin, E., Schwarzer, M., D’Oro, P., Bacon, P., Courville A. (2022). The primacy bias in deep reinforcement learning. ICML.
Krueger, D., Caballero, E., Jacobsen, J., Zhang, A., Binas, J., Zhang, D., Priol, R.L. Courville, A. (2021). Out-of-Distribution Generalization via Risk Extrapolation (REx). In Proceedings of Machine Learning Research. 139:5815-5826
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017). Improved training of wasserstein gans.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.