Mentor
Sokratis Trifinopoulos, Massachusetts Institute of Technology.
Publication Date
2023
Document Type
Paper
DOI
10.25776/v6wj-t617
Pages
1-7 pp.
Abstract
NuCLR (Nuclear Co-Learned Representations) is a cutting-edge multi-task deep learning framework designed to predict essential nuclear observables, including binding energies, decay energies, and nuclear charge radii. As part of the REYES Mentorship Program, we investigated the application of dynamic loss weighting to further refine NuCLR’s predictive performance. Our findings indicate that while weighting strategies can enhance accuracy in specific tasks, such as binding energy prediction, they may underperform in others. Equal Weighting (EW), the original method employed by NuCLR, demonstrated consistent performance across multiple tasks, affirming its robustness. This report succinctly presents the developments and results of the mentorship program and outlines our anticipation for continued collaboration on this and related projects.
Repository Citation
Pérez-Díaz, Víctor Samuel, "NuDyCLR: Nuclear Dynamic Co-Learned Representations" (2023). 2023 REYES Proceedings. 3.
https://digitalcommons.odu.edu/reyes-2023/3