BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Digital Modeling of Reality with Machine Learning - Dr Cengiz Ozti
 reli\, Graphics Lecturer\, Department of Computer Science and Technology\,
  University of Cambridge
DTSTART:20200122T150500Z
DTEND:20200122T155500Z
UID:TALK137668@talks.cam.ac.uk
CONTACT:jo de bono
DESCRIPTION:Building digital models of reality and especially visual reali
 ty\, with all its complexity\, is a difficult but exciting task. Many indu
 stries\, disciplines\, and society overall are relying on accurate digital
  models. The difficulty is amplified by the incomplete\, unstructured\, an
 d noisy observations we base our models on. We have been working on utiliz
 ing\, understanding\, and improving machine learning techniques to tackle 
 various associated problems to realize accurate digital models of reality.
  In this talk\, I will give a brief summary of our efforts and focus on a 
 few interesting techniques such as interpretability of what we learn and d
 ata sampling for effective learning.
LOCATION:Lecture Theatre 2\, Computer Laboratory
END:VEVENT
END:VCALENDAR