2006/03/12 by John W. Clark, JOHN W. CLARK, Haochen Li +1
Earth and Planetary Sciences · Materials Science · Physics and Astronomy · #Cold Fusion and Nuclear Reactions #Machine Learning in Materials Science #Nuclear physics research studies #nucl-th
paper · pdf · doi:10.1142/s0217979206036053
published as Int.J.Mod.Phys.B20:5015-5029,2006 · 15 pages, 1 figure, 13th International Conference on Recent Progress in Many-Body Theories QMBT13
arxiv created 2006/03/12 · openalex publication_date 2006/12/15 · arxiv updated 2009/12/01 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28
Advances in statistical learning theory present the opportunity to develop statistical models of quantum many-body systems exhibiting remarkable predictive power. The potential of such "theory-thin" approaches is illustrated with the application of Support Vector Machines (SVMs) to global prediction of nuclear properties as functions of proton and neutron numbers Z and N across the nuclidic chart. Based on the principle of structural-risk minimization, SVMs learn from examples in the existing database of a given property Y, automatically and optimally identify a set of "support vectors" corresponding to representative nuclei in the training set, and approximate the mapping (Z, N) → Y in terms of these nuclei. Results are reported for nuclear masses, beta-decay lifetimes, and spins/parities of nuclear ground states. These results indicate that SVM models can match or even surpass the predictive performance of the best conventional "theory-thick" global models based on nuclear phenomenology.