Category:

Tutorial

Duration: 1:57:59

2,432 views

15

This tutorial will look at how deep learning methods can be applied to problems in computer vision, most notably object recognition. It will start by motivating the need to learn features, rather than hand-craft them. It will then introduce several basic architectures, explaining how they learn features, and showing how they can be "stacked" into hierarchies that can extract multiple layers of representation. Throughout, links will be drawn between these methods and existing approaches to recognition, particularly those involving hierarchical representations. The final part of the lecture will examine the current performances obtained by feature learning approaches on a range of standard vision benchmarks, highlighting their strengths and weaknesses. The tutorial will conclude with a discussion of vision problems that have yet to be successfully addressed by deep learning. Bio: Rob Fergus is an Associate Professor of Computer Science at the Courant Institute of Mathematical Sciences, New York University. He received a Masters in Electrical Engineering with Prof. Pietro Perona at Caltech, before completing a PhD with Prof. Andrew Zisserman at the University of Oxford in 2005. Before coming to NYU, he spent two years as a post-doc in the Computer Science and Artificial Intelligence Lab (CSAIL) at MIT, working with Prof. William Freeman. He has received several awards including a CVPR best paper prize, a Sloan Fellowship & NSF Career award and the IEEE Longuet-Higgins prize.