BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Lifted Relational Neural Networks - Gustav Šir\, Czech Technical 
 University in Prague
DTSTART:20220517T121500Z
DTEND:20220517T131500Z
UID:TALK171791@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nLifted Relational Neural Networks (LRNNs) were i
 ntroduced as a framework for combining logic programming with neural netwo
 rks for efficient learning of latent relational structures\, such as vario
 us subgraph patterns in molecules. In this talk\, we will re-introduce the
  framework in the context of modern Graph Neural Networks (GNNs). Particul
 arly\, we will showcase how the declarative nature of (differentiable) log
 ic programming in LRNNs can be used to elegantly capture the principles of
  various GNN variants\, and extrapolate to other deep relational learning 
 concepts. Additionally\, we will overview some applications\, computationa
 l performance and practical usage of the framework.\n\n*BIO:*\nGustav is a
  fresh AI/ML post-doc at Czech Technical University. Previously\, he did s
 ome internships at University of York\, Google and IBM research. He focuse
 s on combining relational logic with deep learning.
LOCATION:Zoom
END:VEVENT
END:VCALENDAR