BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Multitask Machine Learning of Collective Variables for Enhanced Sa
 mpling of Rare Events - Dr Lixin Sun\, Microsoft Research\, UK
DTSTART:20221003T130000Z
DTEND:20221003T133000Z
UID:TALK182534@talks.cam.ac.uk
CONTACT:Dr Venkat Kapil
DESCRIPTION:In this talk\, I will present a data-driven machine learning a
 lgorithm (Sun et al.\, JCTC\, 18\, 2022) that is devised to learn collecti
 ve variables with a multitask neural network. In this work\, new ways of l
 abeling atomic configurations and approximating committor function are pro
 posed. The resulting ML-learned collective variable is shown to be an effe
 ctive low-dimensional representation\, capturing the reaction progress and
  guiding effective umbrella sampling to obtain accurate free energy landsc
 apes. This approach enables automated dimensionality reduction for energy 
 controlled reactions in complex systems\, offers a unified and data-effici
 ent framework that can be trained with limited data\, and outperforms sing
 le-task learning approaches\, including autoencoders.
LOCATION:Goldsmiths 1\, Department of Materials Science &amp\; Metallurgy
END:VEVENT
END:VCALENDAR