Deep learning: Extrapolation tool for ab initio nuclear theory
Abstract
Ab initio approaches in nuclear theory, such as the no-core shell model (NCSM), have been developed for approximately solving finite nuclei with realistic strong interactions. The NCSM and other approaches require an extrapolation of the results obtained in a finite basis space to the infinite basis space limit and assessment of the uncertainty of those extrapolations. Each observable requires a separate extrapolation and most observables have no proven extrapolation method. We propose a feed-forward artificial neural network (ANN) method as an extrapolation tool to obtain the ground state energy and the ground state point-proton root-mean-square (rms) radius along with their extrapolation uncertainties. The designed ANNs are sufficient to produce results for these two very different observables in Li from the ab initio NCSM results in small basis spaces that satisfy the following theoretical physics condition: independence of basis space parameters in the limit of extremely large matrices. Comparisons of the ANN results with other extrapolation methods are also provided.
Cite
@article{arxiv.1810.04009,
title = {Deep learning: Extrapolation tool for ab initio nuclear theory},
author = {Gianina Alina Negoita and James P. Vary and Glenn R. Luecke and Pieter Maris and Andrey M. Shirokov and Ik Jae Shin and Youngman Kim and Esmond G. Ng and Chao Yang and Matthew Lockner and Gurpur M. Prabhu},
journal= {arXiv preprint arXiv:1810.04009},
year = {2019}
}
Comments
13 pages, 6 figures. Some typos were fixed, e.g., replaced MSE units for the observables with observables' square units. arXiv admin note: text overlap with arXiv:1803.03215