Laurent Dinh

I am a research scientist at Google Brain (Montréal, Canada) working on probabilistic deep learning. In particular, I have been most interested in the development of deep tractable generative models through invertible mappings, exploring and relaxing this invertibility constraint, and simple reassessments of common assumptions behind deep learning practices, concerning generalization or anomaly detection for example.

I obtained my PhD in deep learning at Mila (Montréal, Canada), under the supervision of Yoshua Bengio. Prior to that I was studying at ECP (Paris, France) in applied mathematics and at ENS Paris-Saclay in machine learning and computer vision. I had the privilege to work in the machine learning group led by Nando de Freitas both at UBC (Vancouver, Canada) and DeepMind (London, United Kingdom), and also at Google Brain (Mountain View, US), under the supervision of Samy Bengio.

A map of Paris from A map of Montréal from