In this talk, we will introduce how machine learning, especially, deep learning is utilized in Facebook. Especially, we will explain how mobile vision team optimizes neural networks for various vision tasks.

Peter joined Facebook in 2014 as Research Scientist. Currently, he is managing the Mobile Vision team on efficient computer vision algorithms for mobile and embedded devices. Before joining Facebook, he was Visiting Assistant Professor in Stanford University, Stanford, USA, working on personalized multimedia system and mobile visual search. He completed his Ph.D. with Prof. Touradj Ebrahimi at the Ecole Polytechnique Fédéral de Lausanne (EPFL), Lausanne, Switzerland, 2012.