分析四元数网络组件对图像分类的影响，提出新激活函数提升性能
Statistical Analysis of the Impact of Quaternion Components in Convolutional Neural Networks
- 通过统计实验对比四元数网络中各组件的性能表现
- 新提出的全四元数ReLU激活函数显著提升模型准确率
- 适合研究神经网络结构设计与四元数计算的学者参考
近年来，针对不同问题提出了多种使用四元数卷积神经网络（QCNN）的模型。尽管四元数卷积层的定义相同，但其他基础组件如池化层、激活函数、全连接层等在四元数域中的适配方式存在差异。然而，这些组件的选择及其相互作用对模型性能的影响尚不明确。理解这些选择对性能的影响对于有效使用QCNN至关重要。本文通过对图像分类任务的实验数据进行统计分析，比较了现有组件的性能表现。此外，我们提出一种新的全四元数ReLU激活函数，利用四元数代数的独特性质，进一步提升了模型性能。
原文摘要 · Abstract (English)
In recent years, several models using Quaternion-Valued Convolutional Neural Networks (QCNNs) for different problems have been proposed. Although the definition of the quaternion convolution layer is the same, there are different adaptations of other atomic components to the quaternion domain, e.g., pooling layers, activation functions, fully connected layers, etc. However, the effect of selecting a specific type of these components and the way in which their interactions affect the performance of the model still unclear. Understanding the impact of these choices on model performance is vital for effectively utilizing QCNNs. This paper presents a statistical analysis carried out on experimental data to compare the performance of existing components for the image classification problem. In addition, we introduce a novel Fully Quaternion ReLU activation function, which exploits the unique properties of quaternion algebra to improve model performance.
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。