ICP Kolloquium: Prof. Michele Ceriotti, 28. Oktober 2021, „Machine learning at the atomic scale”

October 28, 2021

Time: October 28, 2021
Download as iCal:

Prof. Michele Ceriotti
Laboratory of Computational Science and Modelling (COSMO), EPFL Lausanne
Donnerstag, 28. Oktober 2021, 14:00 Uhr

via zoom

 

“Machine learning at the atomic scale”

Abstract :
When modeling materials and molecules at the atomic scale, achieving a realistic level of complexity and making quantitative predictions are usually conflicting goals. Data-driven techniques have made great strides towards enabling simulations of materials in realistic conditions with uncompromising accuracy. In particular, statistical 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 accurate quantum chemical calculations, and making it possible to perform simulations that require thorough statistical sampling without compromising on the accuracy of the electronic structure model.
In this talk, I will argue how data-driven modelling can be rooted in a mathematically rigorous and physically-motivated symmetry-adapted framework, and discuss the benefits of such a principled approach. I will present several examples demonstrating how the combination of machine-learning and atomistic simulations can offer useful insights on the behavior of complex systems, and discuss the challenges towards an integrated modeling framework in which physics- and data-driven steps can be combined to improve the accuracy, the computational efficiency and the transferability of predictions, from interatomic potentials to electronic-structure properties.

List of all events


October 2022

July 2022

June 2022

May 2022

December 2021

November 2021

October 2021

July 2021

June 2021

May 2021

February 2021

January 2021

October 2020

September 2020

February 2020

To the top of the page