Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.09747 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914382912421888 |
|---|---|
| author | Zai, Peiwen Cheng, Wei Zhang, Feng-Shou |
| author_facet | Zai, Peiwen Cheng, Wei Zhang, Feng-Shou |
| contents | Machine learning approaches to nuclear mass prediction have achieved remarkable accuracy, but typically rely on existing theoretical baselines or hand-crafted physics features. Here we demonstrate that these prerequisites can be supplanted by structural inductive biases embedded directly in the network architecture. We present the Cooperative Neural Network (CoNN), which predicts binding energies from raw proton and neutron numbers (Z,N) alone by additively combining four structurally constrained modules: a smooth network for bulk liquid-drop trends, discrete scalar embeddings for shell effects, a learnable two-dimensional grid for regional collective correlations, and a parity-aware network for odd--even staggering. On the AME2020 dataset, the CoNN achieves a root-mean-square deviation of 0.269 MeV across all 3558 nuclei, with 0.419 MeV on a held-out interpolation subset and 0.728 MeV on 122 nuclei newly measured since AME2016, placing it among the most accurate baseline-free approaches to direct mass prediction. Notably, the learned embeddings develop pronounced extrema at canonical magic numbers and the pairing module reproduces the expected odd--even staggering along isotopic chains, both emerging from the data without explicit supervision. These results demonstrate that physically motivated architectural constraints can effectively substitute for feature engineering, establishing architecture as physical prior as a promising paradigm for neural-network mass modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09747 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Architecture as physical prior: cooperative neural network for nuclear masses Zai, Peiwen Cheng, Wei Zhang, Feng-Shou Nuclear Theory Machine learning approaches to nuclear mass prediction have achieved remarkable accuracy, but typically rely on existing theoretical baselines or hand-crafted physics features. Here we demonstrate that these prerequisites can be supplanted by structural inductive biases embedded directly in the network architecture. We present the Cooperative Neural Network (CoNN), which predicts binding energies from raw proton and neutron numbers (Z,N) alone by additively combining four structurally constrained modules: a smooth network for bulk liquid-drop trends, discrete scalar embeddings for shell effects, a learnable two-dimensional grid for regional collective correlations, and a parity-aware network for odd--even staggering. On the AME2020 dataset, the CoNN achieves a root-mean-square deviation of 0.269 MeV across all 3558 nuclei, with 0.419 MeV on a held-out interpolation subset and 0.728 MeV on 122 nuclei newly measured since AME2016, placing it among the most accurate baseline-free approaches to direct mass prediction. Notably, the learned embeddings develop pronounced extrema at canonical magic numbers and the pairing module reproduces the expected odd--even staggering along isotopic chains, both emerging from the data without explicit supervision. These results demonstrate that physically motivated architectural constraints can effectively substitute for feature engineering, establishing architecture as physical prior as a promising paradigm for neural-network mass modeling. |
| title | Architecture as physical prior: cooperative neural network for nuclear masses |
| topic | Nuclear Theory |
| url | https://arxiv.org/abs/2603.09747 |