File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1088/1674-1137/ad021c
- Scopus: eid_2-s2.0-85182694758
- WOS: WOS:001140175800001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Nuclear mass predictions based on a deep neural network and finite-range droplet model (2012)
Title | Nuclear mass predictions based on a deep neural network and finite-range droplet model (2012) |
---|---|
Authors | |
Keywords | deep neural network machine learning nuclear mass |
Issue Date | 1-Feb-2024 |
Publisher | IOP Publishing |
Citation | Chinese Physics C, 2024, v. 48, n. 2, p. 1-12 How to Cite? |
Abstract | A neural network with two hidden layers is developed for nuclear mass prediction, based on the finite-range droplet model (FRDM12). Different hyperparameters, including the number of hidden units, choice of activation functions, initializers, and learning rates, are adjusted explicitly and systematically. The resulting mass predictions are achieved by averaging the predictions given by several different sets of hyperparameters with different regularizers and seed numbers. This can provide not only the average values of mass predictions but also reliable estimations in the mass prediction uncertainties. The overall root-mean-square deviations of nuclear mass are reduced from 0.603 MeV for the FRDM12 model to 0.200 MeV and 0.232 MeV for the training and validation sets, respectively. |
Persistent Identifier | http://hdl.handle.net/10722/340019 |
ISSN | 2023 Impact Factor: 3.6 2023 SCImago Journal Rankings: 1.184 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yiu, To Chung | - |
dc.contributor.author | Liang, Haozhao | - |
dc.contributor.author | Lee, Hiu Ching Jenny | - |
dc.date.accessioned | 2024-03-11T10:41:03Z | - |
dc.date.available | 2024-03-11T10:41:03Z | - |
dc.date.issued | 2024-02-01 | - |
dc.identifier.citation | Chinese Physics C, 2024, v. 48, n. 2, p. 1-12 | - |
dc.identifier.issn | 1674-1137 | - |
dc.identifier.uri | http://hdl.handle.net/10722/340019 | - |
dc.description.abstract | A neural network with two hidden layers is developed for nuclear mass prediction, based on the finite-range droplet model (FRDM12). Different hyperparameters, including the number of hidden units, choice of activation functions, initializers, and learning rates, are adjusted explicitly and systematically. The resulting mass predictions are achieved by averaging the predictions given by several different sets of hyperparameters with different regularizers and seed numbers. This can provide not only the average values of mass predictions but also reliable estimations in the mass prediction uncertainties. The overall root-mean-square deviations of nuclear mass are reduced from 0.603 MeV for the FRDM12 model to 0.200 MeV and 0.232 MeV for the training and validation sets, respectively. | - |
dc.language | eng | - |
dc.publisher | IOP Publishing | - |
dc.relation.ispartof | Chinese Physics C | - |
dc.subject | deep neural network | - |
dc.subject | machine learning | - |
dc.subject | nuclear mass | - |
dc.title | Nuclear mass predictions based on a deep neural network and finite-range droplet model (2012) | - |
dc.type | Article | - |
dc.identifier.doi | 10.1088/1674-1137/ad021c | - |
dc.identifier.scopus | eid_2-s2.0-85182694758 | - |
dc.identifier.volume | 48 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 12 | - |
dc.identifier.isi | WOS:001140175800001 | - |
dc.publisher.place | BRISTOL | - |
dc.identifier.issnl | 1674-1137 | - |