BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Graph Convolutional Networks for Atomic Structures - Rachel Kurchi
 n\, Carnegie Mellon University
DTSTART:20201207T170000Z
DTEND:20201207T173000Z
UID:TALK154633@talks.cam.ac.uk
CONTACT:Bingqing Cheng
DESCRIPTION:I am developing two packages in the Julia programming language
  to facilitate graph-based machine learning in atomic systems: crystals\, 
 surfaces\, molecules\, etc. In this talk\, I will first give a brief tutor
 ial on the math behind graph convolution\, then introduce the packages: Ch
 emistryFeaturization.jl for building and featurizing the atomic graphs\, a
 nd AtomicGraphNets.jl for building and training the models. I will also co
 mpare the capabilities and performance of my code to the Python-based impl
 ementation of a similar model.
LOCATION:virtual ZOOM meeting ID: 263 591 6003\, Passcode: 000042\, https:
 //us02web.zoom.us/j/2635916003?pwd=ZlBEQnRENGwxNmJGMENGMWxjak5nUT09
END:VEVENT
END:VCALENDAR