BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Three Chemical Prediction Problems that AI will Solve (with Our He
 lp)
DTSTART:20241112T151500
DTEND:20241112T161500
DTSTAMP:20260415T100107Z
UID:be969f40796a852a25c8cecbca6a5b2d8e7bc1babab7713fe55b635c
CATEGORIES:Conferences - Seminars
DESCRIPTION:Brett Savoie is the inaugural Coyle Mission Collegiate Profess
 or of Engineering in the Department of Chemical and Biomolecular Engineeri
 ng at the University of Notre Dame. Brett graduated with degrees in chemis
 try and physics from Texas A&M University in 2008\, obtained his Ph.D. in 
 theoretical chemistry from Northwestern University in 2014\, and from 2014
 -2017 was a postdoc with Thomas Miller at Caltech. In 2017\, Brett joined 
 the faculty of the Davidson School of Chemical Engineering at Purdue Unive
 rsity\, where he established an independent research group to develop phys
 ics-based and machine learning methods to characterize and discover new or
 ganic materials. In 2022\, Brett was promoted to the Charles Davidson Asso
 ciate Professor of Chemical Engineering at Purdue University. In July 2024
 \, Brett joined the faculty at Notre Dame to advance computational materia
 ls research and lead the university’s Scientific AI (SAI) initiative. Br
 ett is the recipient of the ACS PRF\, NSF CAREER\, Dreyfus Machine Learnin
 g in the Chemical Sciences\, and ONR YIP awards.\nThe reaction prediction\
 , reaction network prediction\, and product identification problems are ea
 ch pain points in the vision to digitize and automate reaction discovery. 
 In this talk\, I’ll briefly define each of these related problems and ou
 tline our group’s selected approaches to filling these methodological ga
 ps. The common thread for all three is that the maturation of machine lear
 ning approaches—combined with the decades of physics-based methods prece
 ding it—puts the field within reach of “solving” each of these probl
 ems. Of course\, claims to “solve” a problem are sure to invite welcom
 e discussion!
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR