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:20211030T150000Z
UID:TALK164587@talks.cam.ac.uk
CONTACT:104233
DESCRIPTION:We are delighted to invite you to our first talk of Michaelmas
 \, organised alongside the ML in PL Association. We are hosting *Mateusz M
 alinowski* and *Petar Veličković*\, both senior researchers at Google De
 epMind\, in the Cambridge Union’s Debating Chamber.\n\nThe event will be
 gin at 1pm on Saturday 30th October. If you are interested please fill out
  the *registration form* (https://cambridge2021.paperform.co/)\, and see t
 he Facebook event (https://www.facebook.com/events/3071717486404137).\n\nA
 GENDA\n\n1pm - Opening remarks and talk from Petar Veličković\, \n2pm - 
 Talk from Mateusz Malinowski\, \n2:45pm - Break\, \n3pm - Discussion panel
 \, \n4pm - Closing remarks.\n\nSPEAKER BIOS\n\nMateusz Malinowski is a Res
 earch Scientist at DeepMind. His work concerns computer vision\, natural l
 anguage understanding\, reasoning and scalable training. His main contribu
 tion is creating foundations and various methods that answer questions abo
 ut images and proposing a scalable alternative to backprop training mechan
 ism. Mateusz has received a PhD from Max Planck Institute for Informatics 
 and received multiple awards for his contributions to computer vision. \n\
 nPetar Veličković is a Staff Research Scientist at DeepMind\, and an Aff
 iliated Lecturer at the University of Cambridge. He holds a PhD in Compute
 r Science from the University of Cambridge (Trinity College)\, obtained un
 der the supervision of Pietro Liò. His research concerns geometric deep l
 earning—devising neural network architectures that respect the invarianc
 es and symmetries in data (a topic he's co-written a proto-book about). Wi
 thin this area\, Petar focuses on graph representation learning and its ap
 plications in algorithmic reasoning and computational biology. He has publ
 ished relevant research in these areas at both machine learning venues (Ne
 urIPS\, ICLR\, ICML-W) and biomedical venues and journals (Bioinformatics\
 , PLOS One\, JCB\, PervasiveHealth). In particular\, he is the first autho
 r of Graph Attention Networks—a popular convolutional layer for graphs
 —and Deep Graph Infomax—a scalable local/global unsupervised learning 
 pipeline for graphs (featured in ZDNet). Further\, his research has been u
 sed in substantially improving the travel-time predictions in Google Maps 
 (covered by outlets including the CNBC\, Endgadget\, VentureBeat\, CNET\, 
 the Verge and ZDNet).\n\n
LOCATION:Cambridge Union\, 9a Bridge Street\, Cambridge\, CB2 1UB
END:VEVENT
END:VCALENDAR