Pascal Vincent works in artificial intelligence (expert systems, machine learning, robotics).
His current research interests in the statistical machine learning field include unsupervised feature learning, manifold modelling, alternative parameter estimation techniques for energy based models, semi-supervised learning and learning of deep neural-network architectures. His current main focus is on fundamental principles and techniques for extracting meaningful high level distributed representations from raw high dimensional sensory inputs. Vincent’s work on regularizing auto-encoders (denoising and contractive variants) for unsupervised feature and deep network learning was at the heart of the strategy that won the 2011 Unsupervised and Transfer Learning Challenge.
- Rifai, S. et al. "The Manifold Tangent Classifier." In Proceedings of NIPS 24, NIPS conference 2011, 2294–2302.
- Mesnil, G. et al. "Unsupervised and Transfer Learning Challenge: a Deep Learning Approach." In JMLR: Workshop and Conference Proceedings 2011, 1–15.
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta, Ontario, and Quebec as well as foundations, individuals, corporations, and international partner organizations.