BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine Learning Like a Physicist
DTSTART:20181120T123000
DTSTAMP:20260429T181855Z
UID:84d793a105a56c8f87190805db893f53a1e92140daaa70ad307f0a71
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Michele Ceriotti\nStatistical regression techniques have
  become very fashionable as a tool to predict the properties of systems at
  the atomic scale\, sidestepping much of the computational cost of first-p
 rinciples simulations and making it possible to perform simulations that r
 equire thorough statistical sampling without compromising on the accuracy 
 of the electronic structure model.\nIn this talk I will argue how data-dri
 ven modelling can be rooted in a mathematically rigorous and physically-mo
 tivated framework\, and how this is beneficial to the accuracy and the tra
 nsferability of the model. I will also highlight how machine learning - de
 spite amounting essentially at data interpolation - can provide important 
 physical insights on the behavior of complex systems\, on the synthesizabi
 lity and on the structure-property relations of materials.\nI will give ex
 amples concerning all sorts of atomistic systems\, from semiconductors to 
 molecular crystals [1]\, and properties as diverse as drug-protein interac
 tions[2]\, dielectric response of aqueous systems[3] and NMR chemical shie
 lding in the solid state[4
LOCATION:BSP 234 https://plan.epfl.ch/?room==BSP%20234
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR