BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Active Machine Learning: From Theory to Practice - Robert Nowak\, 
 McFarland-Bascom Professor in Engineering at the University of Wisconsin-M
 adison
DTSTART:20180319T120000Z
DTEND:20180319T130000Z
UID:TALK96886@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION:The field of ML has advanced considerably in recent years\, bu
 t mostly in well-defined domains using huge amounts of human-labeled train
 ing data. Machines can recognize objects in images and translate text\, bu
 t they must be trained with more images and text than a person can see in 
 nearly a lifetime. Humans\, on the other hand\, can learn from far fewer e
 xamples\, generalize well across tasks and modalities\, and perform better
  than machines at most tasks\, especially in complex and unpredictable sit
 uations. To address this gap\, this talk focuses on active ML that close t
 he loop on machine learning\, sensing and data collection\, and human labe
 ling. Standard (passive) machine learning involves designing a classificat
 ion rule based on a randomly selected training dataset. Active machine lea
 rning algorithms automatically and adaptively select the most informative 
 data for labeling so that human time is not wasted labeling irrelevant or 
 trivial examples. The aim is to make ML as efficient and robust as possibl
 e\, with a minimal amount of human supervision and assistance.  This talk 
 describes ongoing theoretical and experimental work in several areas of ac
 tive learning\n\nShort biography:\nRob is the McFarland-Bascom Professor i
 n Engineering at the University of Wisconsin-Madison\, where his research 
 focuses on signal processing\, machine learning\, optimization\, and stati
 stics. 
LOCATION:Department of Engineering - LT2
END:VEVENT
END:VCALENDAR