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

Uloženo v:
Podrobná bibliografie
Vydáno v:Australian and New Zealand Control Conference (Online) s. 122 - 125
Hlavní autoři: Takahashi, Kazuhiko, Shibata, Sora, Hashimoto, Masafumi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 25.11.2021
Témata:
Backpropagation
Control systems
Nonlinear systems
Quaternions
Recurrent neural networks
Simulation
System identification
ISSN:2767-7257
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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