Skip to content

Hugo Larochelle


  • Associate Fellow
  • Canada CIFAR AI Chair
  • Learning in Machines & Brains
  • Pan-Canadian AI Strategy




Hugo Larochelle is a computer scientist whose research focuses on machine learning, i.e., on the development of algorithms capable of extracting concepts and abstractions from data.

He is particularly interested in deep neural networks, mostly applied in the context of big data and to artificial intelligence problems such as computer vision and natural language processing.

More specifically, his research mainly addresses the following topics:

Tasks – supervised, semi-supervised and unsupervised learning, structured output prediction, ranking, density estimation;

Models – deep learning, neural networks, autoencoders, Boltzmann machines, Markov random fields;

Applications – object recognition and tracking, document classification, information retrieval.


  • Google Faculty Research Award, 2013 and 2012
  • NSERC Discovery Grant, 2012
  • AISTATS Notable Paper Award, 2011

Relevant Publications

  • Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F. & Lempitsky, V. (2016). Domain-adversarial training of neural networks. The Journal of Machine Learning Research, 17(1), 2096-2030.
  • Ravi, S., & Larochelle, H. (2016). Optimization as a model for few-shot learning.
  • Larochelle, H., & Murray, I. (2011, June). The neural autoregressive distribution estimator. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (pp. 29-37).
  • Bengio, Y. et al. "Greedy layer-wise training of deep networks." Adv. Neural Inf. Process. Syst 19 (January 2007).

Support Us

CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.

MaRS Centre, West Tower
661 University Ave., Suite 505
Toronto, ON M5G 1M1 Canada