BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ZContent.net//ZapCalLib 1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
SUMMARY:What does a machine learn? A look into the learning process of auto
 mating predictions in chemical problems
LOCATION:Virtual Seminar
TZID:America/Denver
DTSTART:20201112T163000
UID:2026-09-29-12-07-13@natsci.colostate.edu
DTSTAMP:20260929T120713
Description:Literature Seminar\n\nUsage of data driven approaches such as m
 achine learning (ML) is raising due to the success they achieve in predict
 ing outcomes in chemical problems.  However\, there has been constant cri
 ticism from the scientific community about what do the ML based predictive
  models learn from the input data. A small step into understanding the lea
 rning process of ML methods was made by the Zimmermann group in University
  of Michigan. In the recently published paper [1]\, the authors examine va
 rious input representations for a same set of data to understand how the M
 L models learn. The chemical problem considered in the study involves pr
 ediction of activation barriers of atmospheric reactions using the various
  input representations. Upon decoding how ML models learn\, the authors c
 ompare the prediction results from ML based models to an already existing 
 simple chemical relationship i.e.\, Evan-Polanyi relationship. Finally\, t
 he authors address how chemical understanding is necessary for better pred
 ictions using ML techniques.\n\n&nbsp\;\n\n[1] J. A. Kammeraad\, J. Goetz
 \, E.  A. Walker\, A. Tewari\, and P. M. Zimmerman.  J. Chem. Inf. Mode
 l. 2020\, 60\, 1290−1301\n\nZoom Link 4:30 pm
END:VEVENT
END:VCALENDAR