dorsal/arxiv
View SchemaModeling Nuclear Properties with Support Vector Machines
| Authors | Haochen Li, J. W. Clark, E. Mavrommatis, S. Athanassopoulos, K. A. Gernoth |
|---|---|
| Categories | |
| ArXiv ID | nucl-th/0506080 |
| URL | https://arxiv.org/abs/nucl-th/0506080 |
| Journal | Condensed Matter Theories, Vol. 20, edited by J. W. Clark, R. M. Panoff, and H. Li (Nova Science Publishers, Hauppauge, NY, 2005) |
Abstract
We have made initial studies of the potential of support vector machines (SVM) for providing statistical models of nuclear systematics with demonstrable predictive power. Using SVM regression and classification procedures, we have created global models of atomic masses, beta-decay halflives, and ground-state spins and parities. These models exhibit performance in both data-fitting and prediction that is comparable to that of the best global models from nuclear phenomenology and microscopic theory, as well as the best statistical models based on multilayer feedforward neural networks.
{
"annotation_id": "70f7929d-f21f-496e-a255-ae06e57b291f",
"date_created": "2026-03-02T18:00:04.801000Z",
"date_modified": "2026-03-02T18:00:04.801000Z",
"file_hash": "8189c2f4f739920485c1fd5f6b1707f5edce8cb3cbe030f747882f8ba1b2cc1c",
"private": false,
"record": {
"abstract": "We have made initial studies of the potential of support vector machines\n(SVM) for providing statistical models of nuclear systematics with demonstrable\npredictive power. Using SVM regression and classification procedures, we have\ncreated global models of atomic masses, beta-decay halflives, and ground-state\nspins and parities. These models exhibit performance in both data-fitting and\nprediction that is comparable to that of the best global models from nuclear\nphenomenology and microscopic theory, as well as the best statistical models\nbased on multilayer feedforward neural networks.",
"arxiv_id": "nucl-th/0506080",
"authors": [
"Haochen Li",
"J. W. Clark",
"E. Mavrommatis",
"S. Athanassopoulos",
"K. A. Gernoth"
],
"categories": [
"nucl-th"
],
"journal_ref": "Condensed Matter Theories, Vol. 20, edited by J. W. Clark, R. M.\n Panoff, and H. Li (Nova Science Publishers, Hauppauge, NY, 2005)",
"title": "Modeling Nuclear Properties with Support Vector Machines",
"url": "https://arxiv.org/abs/nucl-th/0506080"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "eb8fd12b-4e19-41b1-8495-fa7275e7fab1",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}