BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Generative Models of Molecules in 3D Space - José Miguel Her
 nández Lobato
DTSTART:20200330T153000Z
DTEND:20200330T160000Z
UID:TALK141337@talks.cam.ac.uk
CONTACT:Bingqing Cheng
DESCRIPTION:Computing equilibrium states for many-body systems\, such as m
 olecules\, is a long-standing challenge. In the absence of methods for gen
 erating\nstatistically independent samples\, great computational effort is
  invested in simulating these systems using\, for example\, Markov chain M
 onte\nCarlo. We present a probabilistic model that generates such samples 
 for molecules from their graph representations. Our model learns a low-dim
 ensional manifold that preserves the geometry of local atomic neighborhood
 s through a principled learning representation that is based on Euclidean 
 distance geometry. In a new benchmark for molecular conformation generatio
 n\, we show experimentally that our generative model achieves state-of-the
 -art accuracy. Finally\, we show how to use our model as a proposal distri
 bution in an importance sampling scheme to compute molecular properties.\n
 \nJoin Zoom Meeting\nhttps://zoom.us/j/2635916003\n\nMeeting ID: 263 591 6
 003\n
LOCATION:virtual ZOOM meeting ID: 263 591 6003\, https://zoom.us/j/2635916
 003
END:VEVENT
END:VCALENDAR