利用线性特征解耦方法提升深度学习拟合非线性薛定谔方程的精度
信号处理
2024-11-08 v1 机器学习
摘要
我们利用特征解耦分布(Feature Decoupling Distributed, FDD)方法增强了深度学习拟合非线性薛定谔方程(NLSE)的能力,与非解耦模型相比显著降低了 NLSE 损失。
引用
@article{arxiv.2411.04511,
title = {Improve the Fitting Accuracy of Deep Learning for the Nonlinear Schr\"odinger Equation Using Linear Feature Decoupling Method},
author = {Yunfan Zhang and Zekun Niu and Minghui Shi and Weisheng Hu and Lilin Yi},
journal= {arXiv preprint arXiv:2411.04511},
year = {2024}
}