TL;DR本文通过应用 Hamilton 神经网络来学习和利用物理系统中保守量的对称约束，通过适当的损失函数来实现周期坐标的强制，从而在简单的经典动力学任务中实现了更高的准确性，进而拟合出网络中的隐向量的解析式，从中发现利用了保守量，如角动量。
Abstract
The dynamics of physical systems is often constrained to lower dimensional sub-spaces due to the presence of conserved quantities. Here we propose a method to learn and exploit such symmetry constraints building