BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Opportunities and Challenges in Generative Adversarial Networks: L
 ooking beyond the Hype - Sebastian Nowozin. Principal Researcher\, Machine
  Intelligence and Perception group\, Microsoft Research\, Cambridge\, UK
DTSTART:20180213T140000Z
DTEND:20180213T150000Z
UID:TALK100711@talks.cam.ac.uk
CONTACT:Damon Wischik
DESCRIPTION:Generative Adversarial Networks (GANs) have breathed new life 
 into research on generative models.  Generative models promise to be able 
 to learn rich structural representations from unsupervised data\, enabling
  data-efficient modelling in complex domains.  The talk is divided into th
 ree parts.\n* The first part introduces the basic GAN approach\, understan
 ding it both on the statistical level in terms of minimizing a divergence 
 between probability distributions and algorithmically in terms of a smooth
  two-player game.\n* The second part discusses problems in the GAN approac
 h and consolidates recent research by highlighting problems both in the st
 atistical viewpoint (existence of divergences) and in the algorithmic view
 point (convergence of the GAN game)\, making recommendations for practical
  use of GAN models.\n* The third part discusses the relationship to other 
 generative modelling approaches\, potential applications of GANs and GAN-t
 ype approximations\, and raises open problems for future research.\n\n\nSp
 eaker:\nSebastian Nowozin\, Principal Researcher\, Machine Intelligence an
 d Perception group\, Microsoft Research\, Cambridge\, UK\n\nBio:\nSebastia
 n Nowozin is a machine learning researcher and manager of the Machine Inte
 lligence and Perception group at Microsoft Research Cambridge\, UK.  He co
 mpleted his PhD in 2009 at the Max Planck Institute for Biological Cyberne
 tics in Tübingen\, Germany.  His research is in the area of probabilistic
  models\, deep learning\, and applications to computer vision problems.  H
 is research has received awards including best paper prizes at CVPR and th
 e pattern recognition award from the German Pattern Recognition Society.  
 At Microsoft his research and code has been shipped in Xbox\, Azure ML\, a
 nd Hololens.
LOCATION:Centre for Mathematical Sciences\, MR4
END:VEVENT
END:VCALENDAR