BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Gaussian processes and variational propagation of uncertainty
  - Andreas Damianou - Sheffield University
DTSTART:20150629T100000Z
DTEND:20150629T110000Z
UID:TALK59975@talks.cam.ac.uk
CONTACT:12852
DESCRIPTION:The complex and potentially high-dimensional nature of real wo
 rld data renders them difficult to visualise\, understand and predict. Thi
 s talk will discuss a family of Bayesian approaches for solving the aforem
 entioned problems by combining the flexibility of Gaussian processes with 
 the expressiveness of graphical and latent variable models. The general fr
 amework is referred to as a deep Gaussian process\, from which interesting
  special cases emerge\, for example time-series and multi-view models. The
  framework is accompanied by algorithmic pipelines which automate the proc
 ess of learning rich representations from the data. To achieve principled 
 regularisation it is essential to communicate the uncertainty across the d
 ifferent stages of the pipelines and the different components of the graph
 ical models. Therefore\, the talk will also present a set of mathematical 
 developments which achieve this through variational inference. The above c
 oncepts and algorithms will be demonstrated with examples from computer vi
 sion (high-dimensional video\, images)\, robotics (motion capture data\, h
 umanoid robotics) and dynamical systems.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR