BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Prediction rigidities for atomistic ML models - Sanggyu Chong\, EP
 FL
DTSTART:20240909T133000Z
DTEND:20240909T143000Z
UID:TALK220876@talks.cam.ac.uk
CONTACT:Alexander R Epstein
DESCRIPTION:The widespread application of atomistic machine learning (ML) 
 in the chemical sciences has made it very important to understand how the 
 models learn to correlate chemical structures with their properties\, and 
 what can be done to improve the training efficiency whilst guaranteeing in
 terpretability and transferability. In this work\, we demonstrate the wide
  utility of prediction rigidities\, a family of metrics derived from the l
 oss function\, in understanding the robustness of atomistic ML model predi
 ctions. We show that the prediction rigidities allow the assessment of the
  model not only at the global level for uncertainty quantification\, but a
 lso on the local or the component-wise level at which the intermediate (e.
 g. atomic\, body-ordered\, or range-separated) predictions are made. This 
 allows for an understanding of the model's learning behavior\, and helps t
 o guide efficient dataset construction for training.
LOCATION:Yusuf Hamied Department of Chemistry\, Wolfson Lecture Theatre
END:VEVENT
END:VCALENDAR