用超复数神经网络生成隐藏特征，提升模型效率
Ghost Features and Spooky Transfer Learning for Hypercomplex-Valued Neural Networks
- 构建超复数层，实部为传统输出，虚部生成增强特征
- 虚部特征（幽灵特征）可显著提升网络性能
- 通过幽灵迁移学习整合特征，适合高效模型设计
超复数在复数基础上引入更多虚部分量，不仅提升维度，其虚部运算还具备代数与几何特性，有助于机器学习任务。本文提出一种超复数神经网络层结构，其中实部对应传统实值层输出，虚部则生成称为「幽灵特征」的增强信息，这些特征在实值层中不可见。进一步提出「幽灵迁移学习」方法，可有效将幽灵特征融入已训练网络，充分利用其丰富信息，实现更高效的神经网络。代码与Jupyter Notebook已在https://github.com/mevalle/v-nets/公开。
原文摘要 · Abstract (English)
Hypercomplex numbers extend the concept of complex numbers by introducing additional imaginary components. Besides increasing dimensionality, operations on the imaginary parts provide algebraic and geometrical properties that can be beneficial for solving machine learning problems. In this paper, we show how to create hypercomplex-valued neural network layers where the real part corresponds to the output of a traditional real-valued layer. The additional imaginary parts of these hypercomplex-valued layers produce what we call ``ghost features,'' which contain enhanced information that is not present in the output of the real-valued layer. Moreover, ghost features can be effectively integrated into a trained neural network through a process we refer to as ``spooky transfer learning.'' This approach allows us to harness the richness of ghost features, leading to more efficient neural networks. The source code and Jupyter Notebook are available at https://github.com/mevalle/v-nets/.
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。