Pascal Vincent

Pascal Vincent is an Associate Professor at the Department of Computer Science and Operational Research, University of Montreal, and a key member of the Montreal Institute for Learning Algorithms (MILA). He holds a PhD in Computer Science from the University of Montreal and has been pivotal in advancing machine learning and artificial perception.

• Education: PhD in Computer Science (University of Montreal, 2003)

His research spans machine learning, deep learning, representation learning, and neural networks, focusing on unsupervised methods and geometrically inspired algorithms. He explores how intelligent systems can autonomously build meaningful representations from raw data, driven by principles like the manifold hypothesis.

Key projects include generative stochastic networks, contractive autoencoders, and high-dimensional sequence transduction. His work has resulted in 15+ recent publications in top venues like NIPS, ICML, and CVPR.

Scientific Awards:

• Best student-paper award at ICML 2012
• Honorable mention at NIPS 2011
• Funded by FCI, FRQNT, CRSNG, CIFAR, and IBM

Pascal has supervised 15+ doctoral and Master’s students, including Florian Bordes, Tom Bosc, and Nicolas Boulanger-Lewandowski, across topics like representation learning and generative models. He is also a co-founder of the UNIQUE (Union Neurosciences & Intelligence Artificielle Québec) research consortium.