BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Lennard-Jones Centre
SUMMARY:Anisotropic machine learning representations for c
 oarse-graining - Arthur Lin\, University of Wiscon
 sin–Madison
DTSTART;TZID=Europe/London:20241021T143000
DTEND;TZID=Europe/London:20241021T150000
UID:TALK222889AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/222889
DESCRIPTION:Machine learning (ML) methods have revolutionized 
 atomistic simulations\, enabling highly accurate s
 imulations and analyses at the fraction of the com
 putational cost.  Central to these advances is the
  use of atom-centered numerical representation of 
 the atomistic system\, where one transforms the co
 ordinates and identities of each atom in a way tha
 t preserves the symmetries of the system. However\
 , atom-centered representations\, such as the popu
 lar Smooth Overlap of Atomic Positions (SOAP)\, ar
 e not as well suited for describing large macromol
 ecular systems\; in such cases\, one would likely 
 be more interested in understanding how groups of 
 atoms interact with each other\, either from a sci
 entific or efficiency standpoint. To properly crea
 te a representation for groups of atoms\, we intro
 duce an anisotropic generalization of SOAP\, which
  we deem AniSOAP. This generalized descriptor can 
 describe the complex molecular geometries and capt
 ure orientation-dependent interactions that occur 
 between groups of atoms. In this talk\, I will pre
 sent three different case studies that use AniSOAP
 \, ranging from unsupervised analyses of liquid cr
 ystals to learning complicated benzene energetics.
  From these studies\, AniSOAP gives us a data-driv
 en way to observe how the molecular geometry influ
 ences the formations of certain phases or the ener
 getics of particular configurations. I will then c
 onclude the talk by describing how AniSOAP can be 
 incorporated into a generalized coarse-grained sim
 ulation framework\, and provide my thoughts on how
  it can be used to quantify information-loss incur
 red within coarse-graining.\n
LOCATION:Zoom link: https://zoom.us/j/92447982065?pwd=RkhaY
 kM5VTZPZ3pYSHptUXlRSkppQT09
CONTACT:Eszter Varga-Umbrich
END:VEVENT
END:VCALENDAR