Pages

Thursday, July 30, 2009

CS: Bring out the popcorn, MLSS09 videos are out.

Bring out the popcorn because if you thought you'd have a dull summer the organizers at the Machine Learning Summer School on Theory and Practice of Computational Learning, MLSS09 decided to steer you away from boredom by getting most of the talks/tutorials on video (big kudos to Mikhail Belkin, Partha Niyogi, Steve Smale).The site of the conference is here. First video features a tutorial of 3 hours (cut in three parts) by Emmanuel Candes on An Overview of Compressed Sensing and Sparse Signal Recovery via L1 Minimization (part 2 of the tutorial is the Compressed Sensing presentation).

Description
In many applications, one often has fewer equations than unknowns. While this seems hopeless, the premise that the object we wish to recover is sparse or nearly sparse radically changes the problem, making the search for solutions feasible. This lecture will introduce sparsity as a key modeling tool together with a series of little miracles touching on many areas of data processing. These examples show that finding *that* solution to an underdetermined system of linear equations with minimum L1 norm, often returns the ''right'' answer. Further, there is by now a well-established body of work going by the name of compressed sensing, which asserts that one can exploit sparsity or compressibility when acquiring signals of general interest, and that one can design nonadaptive sampling techniques that condense the information in a compressible signal into a small amount of data - in fewer data points than were thought necessary. We will survey some of these theories and trace back some of their origins to early work done in the 50's. Because these theories are broadly applicable in nature, the tutorial will move through several applications areas that may be impacted such as signal processing, bio-medical imaging, machine learning and so on. Finally, we will discuss how these theories and methods have far reaching implications for sensor design and other types of designs.

Of related interest two tutorials:
that are also both about 3 hours long. And then several 1 hour presentations:


All of them are featured on the Compressive Sensing Videos page.

Image Credit: Thierry Legault. Stunning photo of the space shuttle Endeavor docked with the International Space Station crossing the face of the sun. Via Wired.

No comments:

Post a Comment