BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Adding functionality to machine-learning potentials: going beyond 
 accuracy and speed - Miguel Caro\, Aalto University
DTSTART:20231120T143000Z
DTEND:20231120T150000Z
UID:TALK207292@talks.cam.ac.uk
CONTACT:Eszter Varga-Umbrich
DESCRIPTION:Machine learning potentials (MLPs) have emerged in recent year
 s as powerful tools for atomistic materials modeling. The pace of developm
 ent of these MLPs has been formidable\, and nowadays new or modified frame
 works appear in the literature monthly. To some degree\, the developments 
 have focused on winning the race for speed and accuracy\, somewhat sidelin
 ing the fundamental issues related to the locality (or "shortsightedness" 
 of MLPs). At the same time\, the flexibility of ML models allows us to com
 bine MLPs\, i.e.\, the modeling of the potential energy surface\, with obs
 ervables that can be directly compared with experiment\, like spectroscopi
 c measurements. In this presentation I will discuss work that we have done
  on these "augmented" MLP simulations\, and how they can help us understan
 d and predict the structure and properties of materials beyond the accurat
 e (and fast) description of bonded interatomic interactions.
LOCATION:Zoom link: https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHpt
 UXlRSkppQT09
END:VEVENT
END:VCALENDAR