Modelling Atomic Properties with the Atomic Cluster Expansion - IPAM at UCLA
Institute for Pure & Applied Mathematics (IPAM) via YouTube
AI Engineer - Learn how to integrate AI into software applications
Become an AI & ML Engineer with Cal Poly EPaCE — IBM-Certified Training
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Explore a comprehensive lecture on the atomic cluster expansion method for constructing hybrid mechanistic and data-driven interatomic potentials. Delve into the principles of this polynomial regression scheme, examining its simplicity, high performance, interpretability, and excellent generalization properties. Discover how the atomic cluster expansion can be applied to various atomic properties, including linear and nonlinear, invariant or covariant, and atomic or global characteristics. Gain insights into emerging models based on ACE methodology and understand attempts to rigorously justify the atomic cluster expansion from first principles. Learn how complex many-body models can be decomposed into local and low-dimensional components through different approaches.
Syllabus
Christoph Ortner - Modelling Atomic Properties with the Atomic Cluster Expansion - IPAM at UCLA
Taught by
Institute for Pure & Applied Mathematics (IPAM)