Hugo Larochelle, Ph. D.
Doctor Hugo Larochelle’ research focuses on the development of learning algorithms for training deep neural networks (deep learning). The objective is to find procedures for a network of artificial neurons to learn, from example, how to reproduce human behavior. He is particularly interested in deep networks which, like the human brain, contain several layers of neurons interacting together in complex ways.
Deep neural networks can be applied to several problems of artificial intelligence such as computer vision and natural language processing.
- Hugo Larochelle, Iain Murray. The Neural Autoregressive Distribution Estimator. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011
- Hugo Larochelle, Geoffrey Hinton. Learning to Combine Foveal Glimpses with a Third-order Boltzmann Machine. Advances in Neural Information Processing Systems 23, Pages 1243-1251, 2010
- Hugo Larochelle, Yoshua Bengio, Jérôme Louradour, Pascal Lamblin. Exploring Strategies for Training Deep Neural Networks. Journal of Machine Learning Research, Volume 10, Pages 1-40, 2009
- Yoshua Bengio, Pascal Lamblin, Dan Popovici, Hugo Larochelle. Greedy Layer-Wise Training of Deep Networks. Advances in Neural Information Processing Systems 19, Pages 153-160, 2007
Know-How & Opportunities for Collaboration
- Machine learning
- Neural networks
- Probabilistic modeling
- Computer vision