Improve the Fitting Accuracy of Deep Learning for the Nonlinear
Schrödinger Equation Using Linear Feature Decoupling Method
Asia Communications and Photonics conference and Exhibition (ACP), 2024
Main:3 Pages
4 Figures
Bibliography:1 Pages
Abstract
We utilize the Feature Decoupling Distributed (FDD) method to enhance the capability of deep learning to fit the Nonlinear Schrodinger Equation (NLSE), significantly reducing the NLSE loss compared to non decoupling model.
View on arXivComments on this paper
