Salvato in:
Dettagli Bibliografici
Autori principali: Carney, Meagan, González-Tokman, Cecilia, Kardkasem, Ruethaichanok, Zhang, Hongkun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.09835
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911053897531392
author Carney, Meagan
González-Tokman, Cecilia
Kardkasem, Ruethaichanok
Zhang, Hongkun
author_facet Carney, Meagan
González-Tokman, Cecilia
Kardkasem, Ruethaichanok
Zhang, Hongkun
contents We introduce a method for learning chaotic maps using an improved autoencoder neural network that incorporates a conjugacy layer in the latent space. The added conjugacy layer transforms nonlinear maps into a simple piecewise linear map (the tent map) whilst enforcing dynamical principles of well-known and defective conjugacy functions that increase the accuracy and stability of the learned solution. We demonstrate the method's effectiveness on both continuous and piecewise chaotic one-dimensional maps and numerically illustrate improved performance over related traditional and recently emerged deep learning architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
Carney, Meagan
González-Tokman, Cecilia
Kardkasem, Ruethaichanok
Zhang, Hongkun
Dynamical Systems
We introduce a method for learning chaotic maps using an improved autoencoder neural network that incorporates a conjugacy layer in the latent space. The added conjugacy layer transforms nonlinear maps into a simple piecewise linear map (the tent map) whilst enforcing dynamical principles of well-known and defective conjugacy functions that increase the accuracy and stability of the learned solution. We demonstrate the method's effectiveness on both continuous and piecewise chaotic one-dimensional maps and numerically illustrate improved performance over related traditional and recently emerged deep learning architectures.
title An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
topic Dynamical Systems
url https://arxiv.org/abs/2507.09835