Improving Molecular Modelling with Data-Driven Strategies

Piero Gasparotto, Paul Scherrer Institute
HPCWire: NWChemEx: Computational Chemistry Code for the Exascale Era

Description: Data-driven techniques have become widely used as a tool to understand and predict the properties of systems at the atomic scale, sidestepping much of the human and computational cost typically required by modeling studies in the past. In this talk, I will show applications of unsupervised and supervised learning methods to different classes of materials and properties, highlighting how machine learning can provide important physical insights on the behavior of complex systems, on the synthesizability, and on the structure-property relations of materials.

Click here to join the meeting

Or call in (audio only)

+1 630-556-7958,,375883855#   United States, Big Rock

Phone Conference ID: 375 883 855#