Pascal Vincent is a full time professor at the Department of Computer Sciences and Operations Research at the Université de Montréal, Canada and a researcher at the Montréal Institute for Learning Algorithms (MILA).
His research interests are focused on discovering fundamental computational principles that underlie the extraordinary capabilities to learn from the environment, understand it and adapt to it that characterize intelligence. The development of novel machine learning algorithms based on such principles, and trained on very large data sets is fundamental in the latest technological breakthroughs in artificial intelligence. Pascal Vincent is trying to implement these principles in the next generation of intelligent machines.
His publications are Efficient Exact Update for training Deep Networks in Very Large Sparse Targets and Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation.