Hugo Larochelle
Appointment
Advisory Committee Member
Canada CIFAR AI Chair
Learning in Machines & Brains
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2018
Hugo Larochelle is an associate fellow in CIFAR’s Learning in Machines & Brains program and a Canada CIFAR AI Chair.
He serves as the scientific director at Mila – the Quebec AI Institute and adjunct professor at the Université de Montréal and McGill University. His academic research on the foundations of deep learning has contributed to several conceptual breakthroughs found in modern AI systems, such as zero-shot learning, few-shot learning, autoregressive neural networks and denoising autoencoders.
Previously, he was principal scientist in the Google DeepMind team in Montreal, and associate professor at the University of Sherbrooke. Through the years, he has played an active role in shaping the AI scientific community, including serving on the boards for the Conference on Neural Information Processing Systems (NeurIPS), International Conference on Machine Learning (ICML) and International Conference on Learning Representations (ICLR), three top academic conferences for the field of AI and co-founding the Transactions on Machine Learning Research journal.
Hugo has a popular online course on deep learning and neural networks, freely accessible on YouTube.
Awards
- Best Paper Award, Reinforcement Learning and Decision-Making Symposium (RLDM), 2019
- Notable Paper Award, Artificial Intelligence and Statistics (AISTATS) conference, 2011
Relevant Publications
- Agarwal, R., Singh, A., Zhang, L., Bohnet, B., Rosias, L., Chan, S., Zhang, B., Anand, A., Abbas, Z., Nova, A., Co-Reyes, J. D., Chu, E., Behbahani, F., Faust, A., & Larochelle, H. (2024). Many-shot in-context learning.
- Ravi, S., & Larochelle, H. (2017). Optimization as a model for few-shot learning.
- Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks.
- Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms.
- Larochelle, H., & Murray, I. (2011). The Neural Autoregressive Distribution Estimator.
- Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. A. (2008). Extracting and composing robust features with denoising autoencoders.
- Larochelle, H., Erhan, D., & Bengio, Y. (2008). Zero-data learning of new tasks.