Quantifying uncertainty in machine learning on nuclear binding energy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911235749969920 |
|---|---|
| author | Huang, Mengyao Wendt, Kyle A. Schunck, Nicolas F. Holmbeck, Erika M. |
| author_facet | Huang, Mengyao Wendt, Kyle A. Schunck, Nicolas F. Holmbeck, Erika M. |
| contents | Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory, however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked. Epistemic uncertainties arising from training the same network multiple times for an ensemble of initial weight sets offer a first insight into the confidence of machine learning predictions, but they often come with a high computational cost. Instead, we apply a single-model uncertainty quantification method called Δ-UQ that gives epistemic uncertainties with one-time training. We demonstrate our approach on a 2-feature model of nuclear binding energies per nucleon with proton and neutron number pairs as inputs. We show that Δ-UQ can produce reliable and self-consistent epistemic uncertainty estimates and can be used to assess the degree of confidence in predictions made with deep neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantifying uncertainty in machine learning on nuclear binding energy Huang, Mengyao Wendt, Kyle A. Schunck, Nicolas F. Holmbeck, Erika M. Nuclear Theory Techniques from artificial intelligence and machine learning are increasingly employed in nuclear theory, however, the uncertainties that arise from the complex parameter manifold encoded by the neural networks are often overlooked. Epistemic uncertainties arising from training the same network multiple times for an ensemble of initial weight sets offer a first insight into the confidence of machine learning predictions, but they often come with a high computational cost. Instead, we apply a single-model uncertainty quantification method called Δ-UQ that gives epistemic uncertainties with one-time training. We demonstrate our approach on a 2-feature model of nuclear binding energies per nucleon with proton and neutron number pairs as inputs. We show that Δ-UQ can produce reliable and self-consistent epistemic uncertainty estimates and can be used to assess the degree of confidence in predictions made with deep neural networks. |
| title | Quantifying uncertainty in machine learning on nuclear binding energy |
| topic | Nuclear Theory |
| url | https://arxiv.org/abs/2504.09013 |