BriefGPT.xyz
Jun, 2020
稀疏辛合成神经网络
Sparse Symplectically Integrated Neural Networks
HTML
PDF
Daniel M. DiPietro, Shiying Xiong, Bo Zhu
TL;DR
利用稀疏回归方法，结合四阶辛普森积分法实现了对哈密顿动力学系统的建模，能够在数据有限噪声较大的情况下较好地预测和求出系统规律。
Abstract
We introduce
sparse symplectically integrated neural networks
(SSINNs), a novel model for learning
hamiltonian dynamical systems
from data. SSINNs combine fourth-order
→