BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Atomic Cluster Expansion: A framework for fast and accurate ML for
 ce fields - David P. Kovacs\, University of Cambridge
DTSTART:20220425T130000Z
DTEND:20220425T133000Z
UID:TALK172559@talks.cam.ac.uk
CONTACT:Dr Christoph Schran
DESCRIPTION:In this talk I will describe the Atomic Cluster Expansion (ACE
 ) which provides a systematic framework to derive a formally complete set 
 of symmetric polynomial basis functions. I will show that using the ACE fe
 atures and linear regression we can create highly accurate and fast force 
 fields. I will also show some recent results of using equivariant ACE for 
 the fitting of vectorial properties\, such as dipole moments. Finally\, I 
 will briefly present multi-ACE\, a framework unifying most existing machin
 e learning force fields\, including local models like SOAP-GAP and the mes
 sage passing neural networks.
LOCATION:Pfizer Lecture Theatre\, Department of Chemistry\, Lensfield Road
 \, Cambridge\, CB2 1EW
END:VEVENT
END:VCALENDAR