Thomas Pock on "Learning with energy-based models":
In this talk, I will show how to use learning techniques to significantly improve energy-based models. I will start by showing that even for the simplest models such as total variation, one can greatly improve the accuracy of the numerical approximation by learning the „best“ discretization within a class of consistent discretizations. Then I will move forward to more expressive models and show how they can be learned in order to give state-of-the art performance for image reconstruction problems, such as denoising, superresolution, MRI and CT. Finally, I will show how energy based models for image labeling such as Markov random fields can be used in the framework of deep learning.