Taming nuclear complexity with a committee of multilayer neural networks
| Autor: | Jean-Paul Ebran, David Regnier, R. D. Lasseri, Antonin Penon |
|---|---|
| Přispěvatelé: | Département de Physique Nucléaire (ex SPhN) (DPHN), Institut de Recherches sur les lois Fondamentales de l'Univers (IRFU), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Centre de Mathématiques et de Leurs Applications (CMLA), École normale supérieure - Cachan (ENS Cachan)-Centre National de la Recherche Scientifique (CNRS), Direction des Applications Militaires (DAM), Commissariat à l'énergie atomique et aux énergies alternatives (CEA) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
[PHYS.NUCL]Physics [physics]/Nuclear Theory [nucl-th] Nuclear Theory Computer science Active learning (machine learning) Structure (category theory) FOS: Physical sciences General Physics and Astronomy Computational Physics (physics.comp-ph) 01 natural sciences Nuclear Theory (nucl-th) Set (abstract data type) Chart 0103 physical sciences Atomic nucleus Energy density Deep neural networks [INFO]Computer Science [cs] 010306 general physics Nuclear Experiment Algorithm Physics - Computational Physics Nuclear Physics |
| Zdroj: | Phys.Rev.Lett. Phys.Rev.Lett., 2020, 124 (16), pp.162502. ⟨10.1103/PhysRevLett.124.162502⟩ Physical Review Letters Physical Review Letters, American Physical Society, 2020, 124 (16), pp.162502. ⟨10.1103/PhysRevLett.124.162502⟩ Physical Review Letters, 2020, 124 (16), pp.162502. ⟨10.1103/PhysRevLett.124.162502⟩ |
| ISSN: | 0031-9007 1079-7114 |
| DOI: | 10.1103/PhysRevLett.124.162502⟩ |
| Popis: | International audience; We demonstrate that a committee of deep neural networks is capable of predicting the ground-state and excited energies of more than 1800 atomic nuclei with an accuracy akin to the one achieved by state-of-the-art nuclear energy density functionals (EDFs) and with significantly less computational cost. An active learning strategy is proposed to train this algorithm with a minimal set of 210 nuclei. This approach enables future fast studies of the influence of EDF parametrizations on structure properties over the whole nuclear chart and suggests that for the first time a machine learning framework successfully encoded several correlated aspects of nuclear deformation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|