BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Topological Data Analysis: potential applications to computer visi
 on - Vitaliy Kurlin\, Durham University
DTSTART:20140210T110000Z
DTEND:20140210T120000Z
UID:TALK50650@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Topological Data Analysis quantifies hidden topological struct
 ures in big raw noisy data. The flagship tool (persistent homology) summar
 ises the underlying structure across all scales. The stability result says
  that such a summary (persistence diagram) is robust to noise. We shall re
 view potential approaches to combine topological data analysis and machine
  learning for practical problems in computer vision.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR