BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:DFT is so 2008? - Aaron Kaplan\, Lawrence Berkeley National Labora
 tory (USA)
DTSTART:20260309T140000Z
DTEND:20260309T143000Z
UID:TALK243301@talks.cam.ac.uk
CONTACT:Dr Fabian Berger
DESCRIPTION:Although DFT has long been the workhorse method of computation
 al chemistry\, materials science\, and physics\, all beasts of burden even
 tually need a break. Machine learning interatomic potentials (MLIPs) have 
 recently begun to bridge the divide between chemistry-dependent classical 
 interatomic potentials and DFT. Often covering nearly all the periodic tab
 le\, the accuracy of an MLIP depends heavily on its training data. Extant 
 MLIP-ready datasets\, such as the Materials Project\, tend to be noisy and
  favor basins on the potential energy surface. More recent efforts to purp
 ose-build datasets for training MLIPs have favored maximalist approaches\,
  possibly leading to dataset duplication. In my talk\, I’ll give a broad
  overview of the accuracy and computational considerations entering the co
 nstruction of MLIP datasets\, including relevant background on DFT. I’ll
  then discuss two recent dataset generation efforts I’ve contributed to\
 , MatPES and MP-ALOE\, which have sought to maximize dataset information d
 ensity and accuracy. I’ll finish with an outlook to where these efforts 
 lead.
LOCATION:https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT0
 9
END:VEVENT
END:VCALENDAR