BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Generalizing Convolutions for Deep Learning  - Prof. Max Welling (
 University of Amsterdam)
DTSTART:20170329T120000Z
DTEND:20170329T133000Z
UID:TALK71552@talks.cam.ac.uk
CONTACT:44515
DESCRIPTION:Arguably\, most excitement about deep learning revolves around
  the performance of convolutional neural networks and their ability to aut
 omatically extract useful features from signals. In this talk I will prese
 nt work from AMLAB where we generalize these convolutions. First we study 
 convolutions on graphs and propose a simple new method to learn embeddings
  of graphs which are subsequently used for semi-supervised learning and li
 nk prediction. We discuss applications to recommender systems and knowledg
 e graphs. Second we propose a new type of convolution on regular grids bas
 ed on group transformations. This generalizes normal convolutions based on
  translations to larger groups including the rotation group. Both methods 
 often result in significant improvements relative to the current state of 
 the art.\n\nJoint work with Thomas Kipf\, Rianne van den Berg and Taco Coh
 en.   \n
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR