Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nakayama, Chikara, Yoneda, Tsuyoshi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916413991550976
author Nakayama, Chikara
Yoneda, Tsuyoshi
author_facet Nakayama, Chikara
Yoneda, Tsuyoshi
contents We consider arbitrary bounded discrete time series originating from dynamical system with recursivity. More precisely, we provide an explicit construction of recurrent neural networks which effectively approximate the corresponding discrete dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19278
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems
Nakayama, Chikara
Yoneda, Tsuyoshi
Machine Learning
Dynamical Systems
We consider arbitrary bounded discrete time series originating from dynamical system with recursivity. More precisely, we provide an explicit construction of recurrent neural networks which effectively approximate the corresponding discrete dynamical systems.
title Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems
topic Machine Learning
Dynamical Systems
url https://arxiv.org/abs/2409.19278