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...

Celý popis

Podrobná bibliografia

Vydané v:	Australian and New Zealand Control Conference (Online) s. 122 - 125
Hlavní autori:	Takahashi, Kazuhiko, Shibata, Sora, Hashimoto, Masafumi
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 25.11.2021
Predmet:	Backpropagation Control systems Nonlinear systems Quaternions Recurrent neural networks Simulation System identification
ISSN:	2767-7257
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!