Michael Elad: "Sparse Modeling in Image Processing and Deep Learning"

New Deep Learning Techniques 2018
"Sparse Modeling in Image Processing and Deep Learning"
Michael Elad, Technion - Israel Institute of Technology, Computer Science
Abstract: Sparse approximation is a well-established theory, with a profound impact on the fields of signal and image processing. In this talk we describe two special cases of this model - the convolutional sparse coding (CSC) and its multi-layered version (ML-CSC). We show that the projection of signals (a.k.a. pursuit) to the ML-CSC model leads to various deep convolutional neural network architectures. This connection brings a fresh view to CNN, as we are able to accompany the above by theoretical claims such as uniqueness of the representations throughout the network, and their stable estimation, all guaranteed under simple local sparsity conditions. The 'take-home-message' from this talk is this: The ML-CSC model can serve as the theoretical foundation to deep-learning.
Institute for Pure and Applied Mathematics, UCLA
February 6, 2018
For more information: www.ipam.ucla.edu/programs/wor...

[@suhatuna7946]

Thanks for uploading the video and to Professor for the talk

[@miftahbedru543]

very informative , thank you for uploading this talk

[@CowboyRocksteady]

thank you for uploading!

[@MrArungoel]

Thank you very much for sharing.

[@ujjawalpanchal]

That was amazing!

[@taoyang8204]

awesome

[@lucagagliano5118]

What if the signal is continuous does this theory still apply?

[@abderraoufkhodja7567]

Great