Learning Characteristics of Reverse Quaternion Neural Network

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yamauchi, Shogo, Nitta, Tohru, Ohnishi, Takaaki
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908487127138304
author Yamauchi, Shogo
Nitta, Tohru
Ohnishi, Takaaki
author_facet Yamauchi, Shogo
Nitta, Tohru
Ohnishi, Takaaki
contents The purpose of this paper is to propose a new multi-layer feedforward quaternion neural network model architecture, Reverse Quaternion Neural Network which utilizes the non-commutative nature of quaternion products, and to clarify its learning characteristics. While quaternion neural networks have been used in various fields, there has been no research report on the characteristics of multi-layer feedforward quaternion neural networks where weights are applied in the reverse direction. This paper investigates the learning characteristics of the Reverse Quaternion Neural Network from two perspectives: the learning speed and the generalization on rotation. As a result, it is found that the Reverse Quaternion Neural Network has a learning speed comparable to existing models and can obtain a different rotation representation from the existing models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05816
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Characteristics of Reverse Quaternion Neural Network
Yamauchi, Shogo
Nitta, Tohru
Ohnishi, Takaaki
Neural and Evolutionary Computing
Artificial Intelligence
The purpose of this paper is to propose a new multi-layer feedforward quaternion neural network model architecture, Reverse Quaternion Neural Network which utilizes the non-commutative nature of quaternion products, and to clarify its learning characteristics. While quaternion neural networks have been used in various fields, there has been no research report on the characteristics of multi-layer feedforward quaternion neural networks where weights are applied in the reverse direction. This paper investigates the learning characteristics of the Reverse Quaternion Neural Network from two perspectives: the learning speed and the generalization on rotation. As a result, it is found that the Reverse Quaternion Neural Network has a learning speed comparable to existing models and can obtain a different rotation representation from the existing models.
title Learning Characteristics of Reverse Quaternion Neural Network
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2411.05816