Studies of different kernel functions in nuclear mass predictions with kernel ridge regression
The kernel ridge regression (KRR) approach has been successfully applied in nuclear mass predictions. Kernel function plays an important role in the KRR approach. In this work, the performances of different kernel functions in nuclear mass predictions are carefully explored. The performances are ill...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1061042/full |
| _version_ | 1797894167993516032 |
|---|---|
| author | X. H. Wu |
| author_facet | X. H. Wu |
| author_sort | X. H. Wu |
| collection | DOAJ |
| description | The kernel ridge regression (KRR) approach has been successfully applied in nuclear mass predictions. Kernel function plays an important role in the KRR approach. In this work, the performances of different kernel functions in nuclear mass predictions are carefully explored. The performances are illustrated by comparing the accuracies of describing experimentally known nuclei and the extrapolation abilities. It is found that the accuracies of describing experimentally known nuclei in the KRR approaches with most of the adopted kernels can reach the same level around 195 keV, and the performance of the Gaussian kernel is slightly better than other ones in the extrapolation validation for the whole range of the extrapolation distances. |
| first_indexed | 2024-04-10T07:05:44Z |
| format | Article |
| id | doaj.art-08fe006d569d4fd4aeab2a02a631fac3 |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-04-10T07:05:44Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-08fe006d569d4fd4aeab2a02a631fac32023-02-27T08:20:01ZengFrontiers Media S.A.Frontiers in Physics2296-424X2023-02-011110.3389/fphy.2023.10610421061042Studies of different kernel functions in nuclear mass predictions with kernel ridge regressionX. H. WuThe kernel ridge regression (KRR) approach has been successfully applied in nuclear mass predictions. Kernel function plays an important role in the KRR approach. In this work, the performances of different kernel functions in nuclear mass predictions are carefully explored. The performances are illustrated by comparing the accuracies of describing experimentally known nuclei and the extrapolation abilities. It is found that the accuracies of describing experimentally known nuclei in the KRR approaches with most of the adopted kernels can reach the same level around 195 keV, and the performance of the Gaussian kernel is slightly better than other ones in the extrapolation validation for the whole range of the extrapolation distances.https://www.frontiersin.org/articles/10.3389/fphy.2023.1061042/fullnuclear massmachine-learningkernel ridge regressionkernel functionhyperparameter |
| spellingShingle | X. H. Wu Studies of different kernel functions in nuclear mass predictions with kernel ridge regression Frontiers in Physics nuclear mass machine-learning kernel ridge regression kernel function hyperparameter |
| title | Studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| title_full | Studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| title_fullStr | Studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| title_full_unstemmed | Studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| title_short | Studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| title_sort | studies of different kernel functions in nuclear mass predictions with kernel ridge regression |
| topic | nuclear mass machine-learning kernel ridge regression kernel function hyperparameter |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2023.1061042/full |
| work_keys_str_mv | AT xhwu studiesofdifferentkernelfunctionsinnuclearmasspredictionswithkernelridgeregression |