Go Back

Photo of Pascal Vincent

Pascal Vincent Artificial Intelligence (expert systems - machine learning - robotics)

Pascal Vincent’s current research interests in the statistical machine learning field include unsupervised feature learning, manifold modeling, 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. His work on regularizing auto-encoders (denoising and contractive variants) for unsupervised feature and deep network learning were at the heart of the strategy that won the 2011 Unsupervised and Transfer Learning Challenge.

Relevant Publications

S. Rifai et al, "The Manifold Tangent Classifier," Advances in Neural Information Processing Systems, vol. 24 (NIPS2011), pp. 2294-2302, 2011.

G. Mesnil et al, "Unsupervised and Transfer Learning Challenge: a Deep Learning Approach," ICML 2011 Workshop on Unsupervised and Transfer Learning, in JMLR: Workshop and Conference Proceedings, vol. 7, pp. 1–15, 2011.

Connect

Appointment

Associate Fellow Learning in Machines & Brains

Institution

Université de MontréalDepartment of Computer Science and Operations Research

Education

BEng Ecole Supérieure d'Ingénieurs en Electrotechnique et Electronique

Country

Canada

No Assets Found

Sorry, we did not find any assets matching these filters.