University of Cambridge > Talks.cam > Lennard-Jones Centre > Atomic Cluster Expansion: A framework for fast and accurate ML force fields

Atomic Cluster Expansion: A framework for fast and accurate ML force fields

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Dr Christoph Schran.

This talk will be in hybrid format. Virtual access via: https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT09

In this talk I will describe the Atomic Cluster Expansion (ACE) which provides a systematic framework to derive a formally complete set of symmetric polynomial basis functions. I will show that using the ACE features and linear regression we can create highly accurate and fast force fields. I will also show some recent results of using equivariant ACE for the fitting of vectorial properties, such as dipole moments. Finally, I will briefly present multi-ACE, a framework unifying most existing machine learning force fields, including local models like SOAP -GAP and the message passing neural networks.

This talk is part of the Lennard-Jones Centre series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity