BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Quantum Machine Learning for Accurate and Low-Cost Computational C
 hemistry - Professor Thomas F. Miller III\, Caltech
DTSTART:20210317T160000Z
DTEND:20210317T170000Z
UID:TALK153796@talks.cam.ac.uk
CONTACT:Lisa Masters
DESCRIPTION:Quantum mechanical predictions of ground-state and excited-sta
 te potential energy surfaces and properties face a punishing balance betwe
 en prediction accuracy and computational cost\, creating demand for new me
 thods and modeling strategies. Machine learning (ML) for electronic struct
 ure offers promise in this regard\, although conventional approaches requi
 re vast amounts of high-quality data and offer limited transferability in 
 chemical space. We describe two frameworks for addressing this challenge: 
 Molecular-Orbital-Based Machine Learning [1] and OrbNet [2]. These methods
  focus on training not with respect to atom-based features\, but instead u
 se features based on molecular orbitals\, which have no explicit dependenc
 e on the underlying atom-types and thus provide greater chemical transfera
 bility.  Both methods provide striking accuracy and transferability across
  chemical space while yielding 1000-fold or greater reductions in computat
 ional cost.  \n\n[1] “Improved accuracy and transferability of molecular
 -orbital-based machine learning: Organics\, transition-metal complexes\, n
 on-covalent interactions\, and transition states.” Husch\, Sun\, Cheng\,
  Lee\, and Miller\, JCP\, 154\, 064108 (2021).\n[2] “OrbNet: Deep learni
 ng for quantum chemistry using symmetry-adapted atomic-orbital features. 
 ” Qiao\, Welborn\, Anandkumar\, Manby\, and Miller\, JCP\, 153\, 124111 
 (2020).\n
LOCATION:Zoom: Meeting ID: 974 4858 8660 Passcode: 016125
END:VEVENT
END:VCALENDAR