提出两种新型复数霍普菲尔德网络，通过相位与幅值量化提升状态数。
Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization
- 采用矩形与极坐标系下的截断型激活函数实现复数量化
- 状态数量显著高于已有模型，拓展了应用范围
- 适合需要高存储密度的神经网络设计场景
本文提出两种新型复数霍普菲尔德神经网络（CvHNNs），均引入相位与幅值量化。第一种使用基于复数净输入矩形坐标表示的截断型激活函数；第二种则基于极坐标表示，同样采用截断型激活函数实现相位与幅值量化。所提模型通过量化机制大幅增加状态数量，显著优于文献中现有模型，拓展了复数霍普菲尔德网络的应用潜力。
原文摘要 · Abstract (English)
This research paper introduces two novel complex-valued Hopfield neural networks (CvHNNs) that incorporate phase and magnitude quantization. The first CvHNN employs a ceiling-type activation function that operates on the rectangular coordinate representation of the complex net contribution. The second CvHNN similarly incorporates phase and magnitude quantization but utilizes a ceiling-type activation function based on the polar coordinate representation of the complex net contribution. The proposed CvHNNs, with their phase and magnitude quantization, significantly increase the number of states compared to existing models in the literature, thereby expanding the range of potential applications for CvHNNs.
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。