PulseAugur
实时 17:15:54

Interpretable Neural Networks Leverage Nuclear Symmetries for Mass Prediction

研究人员开发了三种新颖的神经网络模型—FINN、GINN和WINN—来探索核对称性并预测核质量。这些模型在AME2016上训练,并在AME2020数据上进行验证,证明了结合Wigner的SU(4)对称性可以显著降低预测误差。特别是WINN模型,实现了0.430 MeV的低均方根误差,可与最先进的方法相媲美,并提供了对核物理的见解,例如中子滴线附近对称性的恢复以及超重核的行为。 AI

影响 这项研究展示了解释性神经网络如何揭示基本的物理原理,有可能加速其他科学领域的发现。

排序理由 该集群包含一篇学术论文,详细介绍了使用神经网络进行核物理研究的新方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Interpretable Neural Networks Leverage Nuclear Symmetries for Mass Prediction

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Phong Dang, Evander Espinoza, Xiaoliang Wan, Michela Negro, Jerry P. Draayer, Feng Pan, Tomas Dytrych, Daniel Langr, David Kekejian ·

    Bridging Ab Initio Symmetries and Global Nuclear Masses with Interpretable Neural Networks

    arXiv:2606.28287v1 Announce Type: cross Abstract: Ab initio modeling has established Wigner's SU(4) and Elliott's SU(3) as dominant symmetries of the nuclear force in light and intermediate-mass nuclei. We ask whether they also govern nuclear binding across the entire chart. Our …

  2. arXiv cs.LG TIER_1 English(EN) · David Kekejian ·

    利用可解释神经网络连接Ab Initio对称性与全球核质量

    Ab initio modeling has established Wigner's SU(4) and Elliott's SU(3) as dominant symmetries of the nuclear force in light and intermediate-mass nuclei. We ask whether they also govern nuclear binding across the entire chart. Our aim is not high-precision prediction but physical …