Hugo Larochelle
Appointment
Associate Fellow
Canada CIFAR AI Chair
Learning in Machines & Brains
Pan-Canadian AI Strategy
About
Hugo Larochelle is an associate fellow in CIFAR’s Learning in Machines & Brains program and a Canada CIFAR AI Chair at Mila. He is an adjunct professor at the Department of Computer Science and Operations Research (DIRO) at Université de Montréal and the lead of the Google Brain team in Montreal.
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.
Awards
- 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). The neural autoregressive distribution estimator. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (pp. 29-37).
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P. A., & Bottou, L. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research, 11(12).
Bengio, Y. et al. (2007). Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst 19.
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.