AI 中文总结
该研究提出超复数值神经网络的幽灵特征与诡异迁移学习方法，利用超复数虚部生成增强信息的幽灵特征，通过诡异迁移学习将其整合至神经网络，以构建更高效的网络。
AI 中文摘要
超复数通过引入额外虚部拓展了复数的概念，除了提升维度外，虚部的运算还具备代数与几何特性，可助力解决机器学习问题。本文展示如何构建超复数值神经网络层，其中实部对应传统实值层的输出，该超复数值层的额外虚部会生成所谓的“幽灵特征”，其包含实值层输出所不具备的增强信息。此外，幽灵特征可通过名为“诡异迁移学习”的过程有效整合至已训练的神经网络中，该方法能利用幽灵特征的丰富性，构建更高效的神经网络。源代码与Jupyter Notebook可在该URL获取。
英文摘要
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/.
Comments2026 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2026)
