Over the last decade, there have been significant developments in machine learning and artificial intelligence, which are now used frequently in scientific applications. Building on this progress, the focus of this workshop is on the use and future impact of machine learning in nuclear theory and experiments related to the future Electron-Ion Collider (EIC). The EIC is the main effort of the U.S. nuclear physics program where the structure of nucleons/nuclei in terms of quark and gluon degrees of freedom will be explored in great detail. To realize this ambitious program, many challenges in data science and theory remain where AI applications can advance scientific discoveries. Our goal is to bring together machine learning experts and researchers with a focus on hadron and nuclear structure, lattice QCD, nuclear many-body theory, quantum computing, experiment design, and data analysis at collider experiments to discuss recent progress and explore common interests in machine learning tools and applications. The workshop will also focus on connections to AI applications in high-energy physics and heavy-ion collisions at the LHC & RHIC. There are limited slots available for contributed talks. Please contact the organizers with a proposed topic by Friday, September 8th if you would like to attend in person and deliver a talk. The workshop will be primarily in person and limited travel support is available for junior participants.
Specific topics:
- Inverse problems and unfolding
- Generative modeling
- Sampling algorithms for lattice field theory
- Event-level analyses
- Neural network quantum states
- Experimental challenges in nuclear tomography at the EIC
Organizing committee:
Prerit Jaiswal
Dima Kharzeev (SBU/BNL & local CFNS member)
James Mulligan (UCB/LBNL)
Felix Ringer (JLab/ODU)
Nobuo Sato (JLab)
Phiala Shanahan (MIT)
This event is part of the CFNS workshop/ad-hoc meeting series. See the CFNS conferences page for other events.
