BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Prof. Robert Nowak\, University of Wisconsin\; MSR Lectures - Prof
 . Robert Nowak - University of Wisconsin
DTSTART:20100525T130000Z
DTEND:20100525T140000Z
UID:TALK24892@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:*Abstract:* Traditional approaches to sensing and information 
 processing are non-adaptive in the sense that all data are collected prior
  to analysis and processing. One can envision\, however\, adaptive strateg
 ies in which information gleaned from previously collected data is used to
  guide the selection of new data. This talk focuses on the emerging theory
  and practice of such `active learning` methods. I will show that automati
 c feedback from data analysis to data collection can be crucial for effect
 ive learning and inference. To illustrate the role of feedback\, I will di
 scuss two inference problems. First\, I will consider binary-valued predic
 tion (classification) problems. Under a fixed sample budget\, the predicti
 on errors of active learning methods can be exponentially smaller than tho
 se of non-adaptive methods. Second\, motivated by problems in systems biol
 ogy\, I will discuss the role of active learning in the recovery of sparse
  signals in noise. I will show that certain weak\, sparse patterns are imp
 erceptible in non-adaptive measurements\, but can be recovered perfectly u
 sing adaptive sequential experimental designs. \n\n*Biography:* Robert Now
 ak received the B.S. (with highest distinction)\, M.S.\, and Ph.D. degrees
  in electrical engineering from the University of Wisconsin-Madison in 199
 0\, 1992\, and 1995\, respectively.  He was a Postdoctoral Fellow at Rice 
 University in 1995-1996\, an Assistant Professor at Michigan State Univers
 ity from 1996-1999\, held Assistant and Associate Professor positions at R
 ice University from 1999-2003\, and was a Visiting Professor at INRIA in 2
 001. Nowak is now the McFarland-Bascom Professor of Engineering at the Uni
 versity of Wisconsin-Madison and a Visiting Fellow at Trinity College\, Ca
 mbridge.\nHe has served as an Associate Editor for the IEEE Transactions o
 n Image Processing\, the Secretary of the SIAM Activity Group on Imaging S
 cience\, and is currently an Associate Editor for the ACM Transactions on 
 Sensor Networks. He was General Chair for the 2007 IEEE Statistical Signal
  Processing workshop and Technical Program Chair for the 2003 IEEE Statist
 ical Signal Processing Workshop and the 2004 IEEE/ACM International Sympos
 ium on Information Processing in Sensor Networks. Dr. Nowak received the G
 eneral Electric Genius of Invention Award in 1993\, the National Science F
 oundation CAREER Award in 1997\, the Army Research Office Young Investigat
 or Program Award in 1999\, the Office of Naval Research Young Investigator
  Program Award in 2000\, and IEEE Signal Processing Society Young Author B
 est Paper Award in 2000.\nHe is a Fellow of the Institute of Electrical an
 d Electronics Engineers (IEEE).  His research interests include signal pro
 cessing\, machine learning\, imaging and network science\, and application
 s in communications and systems biology.\n
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR