Remarks on System Identification Using a Quaternion Recurrent Neural Network Trained by Backpropagation through Time

This study investigates the learning capability of a quaternion recurrent neural network that is trained based on a backpropagation through time algorithm extended to quaternion numbers. Computational experiments to identify nonlinear systems, e.g. a three-dimensional chaotic system and discrete-tim...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Australian and New Zealand Control Conference (Online) S. 122 - 125
Hauptverfasser: Takahashi, Kazuhiko, Shibata, Sora, Hashimoto, Masafumi
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 25.11.2021
Schlagworte:
Backpropagation
Control systems
Nonlinear systems
Quaternions
Recurrent neural networks
Simulation
System identification
ISSN:2767-7257
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study investigates the learning capability of a quaternion recurrent neural network that is trained based on a backpropagation through time algorithm extended to quaternion numbers. Computational experiments to identify nonlinear systems, e.g. a three-dimensional chaotic system and discrete-time plant, were performed, and the simulation results confirmed the feasibility of using the quaternion recurrent neural network for a control system application.
ISSN:2767-7257
DOI:10.1109/ANZCC53563.2021.9628201