Symplectic convolutional neural networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yıldız, Süleyman, Janik, Konrad, Benner, Peter
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914307063676928
author Yıldız, Süleyman
Janik, Konrad
Benner, Peter
author_facet Yıldız, Süleyman
Janik, Konrad
Benner, Peter
contents We propose a new symplectic convolutional neural network (CNN) architecture by leveraging symplectic neural networks, proper symplectic decomposition, and tensor techniques. Specifically, we first introduce a mathematically equivalent form of the convolution layer and then, using symplectic neural networks, we demonstrate a way to parameterize the layers of the CNN to ensure that the convolution layer remains symplectic. To construct a complete autoencoder, we introduce a symplectic pooling layer. We demonstrate the performance of the proposed neural network on three examples: the wave equation, the nonlinear Schrödinger (NLS) equation, and the sine-Gordon equation. The numerical results indicate that the symplectic CNN outperforms the linear symplectic autoencoder obtained via proper symplectic decomposition.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Symplectic convolutional neural networks
Yıldız, Süleyman
Janik, Konrad
Benner, Peter
Machine Learning
We propose a new symplectic convolutional neural network (CNN) architecture by leveraging symplectic neural networks, proper symplectic decomposition, and tensor techniques. Specifically, we first introduce a mathematically equivalent form of the convolution layer and then, using symplectic neural networks, we demonstrate a way to parameterize the layers of the CNN to ensure that the convolution layer remains symplectic. To construct a complete autoencoder, we introduce a symplectic pooling layer. We demonstrate the performance of the proposed neural network on three examples: the wave equation, the nonlinear Schrödinger (NLS) equation, and the sine-Gordon equation. The numerical results indicate that the symplectic CNN outperforms the linear symplectic autoencoder obtained via proper symplectic decomposition.
title Symplectic convolutional neural networks
topic Machine Learning
url https://arxiv.org/abs/2508.19842