提出反向四元数神经网络，提升旋转表征能力
Learning Characteristics of Reverse Quaternion Neural Network
- 权重反向传播，利用四元数非交换性设计新结构
- 学习速度与现有模型相当，旋转表征更优
- 适合需要精确旋转建模的场景，如三维视觉
本文提出一种新型多层前馈四元数神经网络架构——反向四元数神经网络（Reverse Quaternion Neural Network），利用四元数乘法的非交换特性，探究其学习特性。尽管四元数神经网络已应用于多个领域，但此前尚无研究关注权重反向应用的多层前馈结构。本文从学习速度和旋转泛化两个角度分析该网络特性，结果表明：该模型学习速度与现有模型相当，且能获得不同于传统模型的旋转表示。这为高维空间中的几何建模提供了新的有效工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。