arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.07928cs.LGmath.DS
收藏

具有自动对称性检测的哈密顿神经网络

Hamiltonian Neural Networks with Automatic Symmetry Detection

University of Bremen(不来梅大学);Paderborn University(帕德博恩大学);Saarland University(萨尔大学)

Eva Dierkes, Christian Offen, Sina Ober-Blöbaum, Kathrin Flaßkamp

AI总结:

本文提出结合 Lie 代数框架的增强型 HNN,可自动检测并嵌入哈密顿系统对称性,同时学习对称群作用与总能量,并通过小车摆和二体问题示例验证。

摘要:

最近,哈密顿神经网络(HNN)被提出,用于在学习哈密顿系统的动力学方程时融入先验物理知识。由此,尽管采用数据驱动建模方法,辛系统结构仍得以保持。然而,保持对称性需要额外关注。在本研究中,我们利用 Lie 代数框架增强 HNN,以检测对称性并将其嵌入神经网络。该方法能够同时学习对称群作用和系统的总能量。作为示例,研究考虑了小车上的摆以及天体动力学中的二体问题。

英文摘要:

Recently, Hamiltonian neural networks (HNN) have been introduced to incorporate prior physical knowledge when learning the dynamical equations of Hamiltonian systems. Hereby, the symplectic system structure is preserved despite the data-driven modeling approach. However, preserving symmetries requires additional attention. In this research, we enhance HNN with a Lie algebra framework to detect and embed symmetries in the neural network. This approach allows to simultaneously learn the symmetry group action and the total energy of the system. As illustrating examples, a pendulum on a cart and a two-body problem from astrodynamics are considered.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑