BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Information Theory and Method of Types: Channels\, Quantizers\, an
 d Divergences - Antonio Artés-Rodríguez (University of Cambridge)\, Ying
 zhen Li
DTSTART:20140116T150000Z
DTEND:20140116T163000Z
UID:TALK50245@talks.cam.ac.uk
CONTACT:Konstantina Palla
DESCRIPTION:Information Theory and Machine Learning share many concept\, m
 odels\, and \ninference methods\, and in some cases offers complementary p
 erspective on \na problem. In this RCC we consider one of the latter case:
  quantization (IT) or \nfeature extraction (ML) for classifier’s design.
 \n\nWe will start reviewing the original work of Shannon on noisy channel 
 coding \nand some recent results on this topic. We will continue with its 
 dual problem\, \nrate distortion theory\, and its implementation\, the des
 ign of quantizers. We will\nconsider the use of different divergences for 
 quantizer’s design and we end up \nanalysing its relationship with the l
 oss function for learning the classifier.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR