BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Cambridge Statistics Discussion Group (CSDG)
SUMMARY:Probabilistic machine learning: foundations and fr
 ontiers - Zoubin Ghahramani\, Department of Engine
 ering
DTSTART;TZID=Europe/London:20171010T191500
DTEND;TZID=Europe/London:20171010T213000
UID:TALK69543AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/69543
DESCRIPTION:Probabilistic modelling provides a mathematical fr
 amework for understanding what learning is\, and h
 as therefore emerged as one of the principal appro
 aches for designing computer algorithms that learn
  from data acquired through experience.  I will re
 view the foundations of the field of probabilistic
  machine learning. I will then highlight some curr
 ent areas of research at the frontiers of machine 
 learning\, leading up to topics such as Bayesian d
 eep learning\, probabilistic programming\, Bayesia
 n optimisation\, the rational allocation of comput
 ational resources\, and the Automatic Statistician
 .
LOCATION:Cognition and Brain Sciences Unit\, Chaucer Road\,
  Cambridge
CONTACT:Peter Watson
END:VEVENT
END:VCALENDAR