BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Combining scalar and vector learning to predict molecular dipole m
 oments - David Wilkins\, Queen's University Belfast
DTSTART:20200720T153000Z
DTEND:20200720T160000Z
UID:TALK148633@talks.cam.ac.uk
CONTACT:Bingqing Cheng
DESCRIPTION:The dipole moment of a molecule is vital in understanding its 
 interaction with other molecules and with light (and thus its spectroscopi
 c properties). Despite its importance\, an accurate quantum-chemical calcu
 lation can be computationally expensive\, and sensitive to the computation
 al details. I describe a method for learning molecular dipole moments by c
 ombining two machine-learning methods that each represent a different type
  of physical effect: scalar Gaussian Process Regression (GPR)\, which lear
 ns partial atomic charges and thus resembles charge separation\, and vecto
 r GPR\, which learns partial atomic dipoles and resembles atomic polarizat
 ion. While these two methods have their own advantages and disadvantages\,
  combining the two gives rise to a single method with the best features of
  both\, opening up the way to accurate molecular simulations and calculati
 ons of spectra.
LOCATION:virtual ZOOM meeting ID: 263 591 6003\, https://zoom.us/j/2635916
 003
END:VEVENT
END:VCALENDAR