BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Random Projections - David Lopez-Paz\, David Duvenaud
DTSTART:20131107T150000Z
DTEND:20131107T163000Z
UID:TALK48793@talks.cam.ac.uk
CONTACT:Konstantina Palla
DESCRIPTION:A fundamental result of Johnson and Lindenstrauss states that 
 one may randomly project a collection of data points into a lower dimensio
 nal space while preserving pairwise point distances. How is this possible?
  Recent developments have gone even further: non-linear randomised project
 ions can be used to approximate kernel machines and scale them to datasets
  with millions of features and samples. In this talk we will explore the t
 heoretical aspects of the great Random Projection method\, and perform liv
 e demos to demonstrate its effectiveness.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR