Reconstructing Attractors with Autoencoders

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fainstein, Facundo, Mindlin, Gabriel B., Groisman, Pablo
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911853893910528
author Fainstein, Facundo
Mindlin, Gabriel B.
Groisman, Pablo
author_facet Fainstein, Facundo
Mindlin, Gabriel B.
Groisman, Pablo
contents We show how to train an autoencoder to reconstruct an attractor from recorded footage, preserving the topology of the underlying phase space. This is explicitly demonstrated for the classic finite-amplitude Lorenz atmospheric convection problem.
format Preprint
id arxiv_https___arxiv_org_abs_2404_16855
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reconstructing Attractors with Autoencoders
Fainstein, Facundo
Mindlin, Gabriel B.
Groisman, Pablo
Adaptation and Self-Organizing Systems
Data Analysis, Statistics and Probability
We show how to train an autoencoder to reconstruct an attractor from recorded footage, preserving the topology of the underlying phase space. This is explicitly demonstrated for the classic finite-amplitude Lorenz atmospheric convection problem.
title Reconstructing Attractors with Autoencoders
topic Adaptation and Self-Organizing Systems
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2404.16855