BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neural network potentials in theory and practice - Andreas Singrab
 er\, University of Vienna
DTSTART:20200622T160000Z
DTEND:20200622T163000Z
UID:TALK149671@talks.cam.ac.uk
CONTACT:Bingqing Cheng
DESCRIPTION:Neural network potentials (NNPs) have demonstrated the effecti
 veness of machine-learning tools in the context of atomistic simulations. 
 This approach\, which is based on artificial neural networks trained to ac
 curately reproduce ab initio potential energy surfaces\, offers two major 
 advantages. First\, with respect to the underlying reference method the co
 mputational effort to calculate energies and forces is drastically reduced
 \, which allows to sample large system sizes and long time scales in molec
 ular dynamics simulations. In addition\, unlike empirical potentials\, the
  neural network at the very heart of the method is not limited by an appro
 ximate functional form but can flexibly adjust to the reference potential 
 energy surface.\n\nIn this MLDG tutorial session I will briefly introduce 
 the method\, continue with a presentation of the software package n2p2 and
  provide also real-world examples of NNP training and application.
LOCATION:virtual ZOOM meeting ID: 263 591 6003\, https://zoom.us/j/2635916
 003
END:VEVENT
END:VCALENDAR