BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Encoding quantum-chemical knowledge into machine-learning models -
  Professor Clemence Corminboeuf\, EPFL
DTSTART:20211013T133000Z
DTEND:20211013T143000Z
UID:TALK160807@talks.cam.ac.uk
CONTACT:Lisa Masters
DESCRIPTION:Today many quantum chemists are inspired by tasks such as over
 coming the complexity of the electronic structure problem or bypassing DFT
 /wavefunction-based computations by leveraging machine learning (ML) techn
 iques. Reported applications span from simple atomization energies to comp
 lex mathematical objects\, such as the many body wavefunction. This talk d
 iscusses our strategies exploiting the interplay between quantum chemistry
  and statistical learning techniques.[1-4] We will discuss a ML workflow s
 pecifically adapted to predict the primary output of quantum chemical comp
 utations (e.g.\, ρ(r)\, particle- hole densities\, on-top pair density\, 
 etc.) from which many properties could be derived. These properties range 
 from the electrostatic potential of a protein to a real-space indicator of
  electron correlation.[2-4] Emphasis will also be placed on the importance
  of the quantum chemical metrics chosen for the regression.[1] Finally and
  if time remains\, we will discussed atomistic ML models aiming at more ef
 ficiently learning challenging energetic properties (e.g.\, the enantiomer
 ic excess).\n\n[1] Briling\, K. R.\; Fabrizio\, A.\; Corminboeuf\, C. J. C
 hem. Phys. 2021\, 155\, 024107. [2] Vela\, S.\; Fabrizio\, A.\; Briling\, 
 K. R.\; Corminboeuf\, C. J. Phys. Chem. Lett. 2021\, 12\, 5957. [3] Fabriz
 io\, A.\; Briling K. R.\; Girardier\, D. D.\; Corminboeuf\, C. J. Chem. Ph
 ys. 2020\, 153\, 204111. [4] Fabrizio\, A.\; Grisafi\, A.\; Meyer\, B.\; C
 eriotti\, M.\; Corminboeuf\, C. Chem. Sci. 2019\, 10\, 9424.
LOCATION:Dept of Chemistry\, Wolfson Lecture Theatre and Zoom: Meeting ID:
  915 2897 9304 Passcode: 474419
END:VEVENT
END:VCALENDAR