INT Program 22-1

Machine Learning for Nuclear Theory

March 28 - April 22, 2022

Organizers:

  • Gaute Hagen, Oak Ridge National Laboratory, hageng@ornl.gov

  • Nobuo Sato, Thomas Jefferson National Accelerator Facility, nsato@jlab.org

  • Phiala Shanahan, Massachusetts Institute of Technology, pshana@mit.edu


Diversity Coordinator:

  • Gaute Hagen, Oak Ridge National Laboratory, hageng@ornl.gov


Program Coordinator:


Image credit: Andy Sproles, ORNL

The INT has a new website! Please visit the 22-1 page on our new site.

As of May 5th 2022, the website you are currently viewing will no longer be updated. Please visit the above link to access our new website. If you have questions or feedback about the website, please contact us at intmail@uw.edu

Note to applicants: This is an in-person program. There is no virtual/online option for this event at this time. Please be aware that all participants must show proof of vaccination against COVID-19 upon arrival to the INT.

Disclaimer: Please also be aware that due to ongoing concerns regarding the COVID-19 pandemic, the program may be cancelled, with the exception of the workshop week being changed to an online-only event.

Overview


Over the last decade there has been significant development in machine learning and artificial intelligence, with supervised and unsupervised computational learning tools now used routinely in scientific applications. Building on this progress, the focus of this program is on the use and future impacts of machine learning in nuclear theory, bringing together researchers with focuses in lattice QCD and statistical systems, hadron and nuclear structure, many-body theory, quantum computing, nuclear astrophysics, and hot and dense matter, to explore common interests in machine learning tools and applications.

The week-long embedded workshop is targeted at the exploration of connections to researchers and ideas from related fields including those outside nuclear theory and in the connection to experimental programs such as Jefferson Lab, RHIC, FRIB and the future EIC, as well as discussion of common themes in scientific machine learning including uncertainty quantification, robustness, and the inclusion of physical constraints, and at discussion of the progress required for machine learning for nuclear theory to best utilise state of the art computational resources and exascale computing capabilities.


Program Format


Week 1 - Embedded Workshop

Week 2 - Program

Week 3 - Program

Week 4 - Program