Learning Characteristics of Reverse Quaternion Neural Network
This work addresses a gap in research on reverse-direction weight application in quaternion neural networks, which is incremental for fields using quaternion-based models.
The paper tackles the problem of understanding learning characteristics in multi-layer feedforward quaternion neural networks by proposing a Reverse Quaternion Neural Network that uses non-commutative quaternion products. It finds that this model has learning speed comparable to existing models and achieves different rotation representations.
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.