BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:CuAI x MLinPL: DeepMind - Mateusz Malinowski and Petar Veličkovi
 ć\, Google DeepMind
DTSTART:20211030T120000Z
DTEND:20211030T151500Z
UID:TALK164584@talks.cam.ac.uk
CONTACT:96442
DESCRIPTION:We are excited to invite you to our first talk of Michaelmas\,
  organised alongside the ML in PL Association! It should be a fantastic ev
 ent – we are hosting Mateusz Malinowski and Petar Veličković\, both se
 nior researchers at Google DeepMind\, in the Cambridge Union’s Debating 
 Chamber.\n\nThe event will begin at 1pm on Saturday 30th October. If you a
 re interested please fill out the registration form (https://cambridge2021
 .paperform.co/)\, and see the Facebook event (https://www.facebook.com/eve
 nts/3071717486404137).\n\nAGENDA\n\n1pm - Opening remarks and talk from Pe
 tar Veličković \n2pm - Talk from Mateusz Malinowski \n2:45pm - Break \n3
 pm - Discussion panel \n4pm - Closing remarks \n\nSPEAKER BIOS\n\nMateusz 
 Malinowski is a Research Scientist at DeepMind. His work concerns computer
  vision\, natural language understanding\, reasoning and scalable training
 . His main contribution is creating foundations and various methods that a
 nswer questions about images and proposing a scalable alternative to backp
 rop training mechanism. Mateusz has received a PhD from Max Planck Institu
 te for Informatics and received multiple awards for his contributions to c
 omputer vision. \n\nPetar Veličković is a Staff Research Scientist at De
 epMind\, and an Affiliated Lecturer at the University of Cambridge. He hol
 ds a PhD in Computer Science from the University of Cambridge (Trinity Col
 lege)\, obtained under the supervision of Pietro Liò. His research concer
 ns geometric deep learning—devising neural network architectures that re
 spect the invariances and symmetries in data (a topic he's co-written a pr
 oto-book about). Within this area\, Petar focuses on graph representation 
 learning and its applications in algorithmic reasoning and computational b
 iology. He has published relevant research in these areas at both machine 
 learning venues (NeurIPS\, ICLR\, ICML-W) and biomedical venues and journa
 ls (Bioinformatics\, PLOS One\, JCB\, PervasiveHealth). In particular\, he
  is the first author of Graph Attention Networks—a popular convolutional
  layer for graphs—and Deep Graph Infomax—a scalable local/global unsup
 ervised learning pipeline for graphs (featured in ZDNet). Further\, his re
 search has been used in substantially improving the travel-time prediction
 s in Google Maps (covered by outlets including the CNBC\, Endgadget\, Vent
 ureBeat\, CNET\, the Verge and ZDNet).\n\n
LOCATION:Cambridge Union\, 9a Bridge Street\, Cambridge\, CB2 1UB
END:VEVENT
END:VCALENDAR