Recurrent neural networks are universal approximators

Autor(en): Schaefer, Anton Maximilian
Zimmermann, Hans-Georg
Stichwörter: Computer Science; Computer Science, Artificial Intelligence; dynamical systems; NONLINEAR OPERATORS; recurrent neural networks; system identification; universal approximation
Erscheinungsdatum: 2007
Herausgeber: WORLD SCIENTIFIC PUBL CO PTE LTD
Journal: INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
Volumen: 17
Ausgabe: 4
Startseite: 253
Seitenende: 263
Zusammenfassung: 
Recurrent Neural Networks (RNN) have been developed for a better understanding and analysis of open dynamical systems. Still the question often arises if RNN are able to map every open dynamical system, which would be desirable for a broad spectrum of applications. In this article we give a proof for the universal approximation ability of RNN in state space model form and even extend it to Error Correction and Normalized Recurrent Neural Networks.
Beschreibung: 
16th International Conference on Artificial Neural Networks (ICANN 2006), Athens, GREECE, SEP 10-14, 2006
ISSN: 01290657
DOI: 10.1142/S0129065707001111

Show full item record

Page view(s)

1
Last Week
0
Last month
0
checked on Mar 4, 2024

Google ScholarTM

Check

Altmetric