分类视角下的复值与实值神经网络：非循环数据示例
Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data
摘要：
本文的贡献是双重的。首先，我们展示了复值神经网络（CVNN）对复值数据集分类任务的潜在兴趣。为了突出这一论断，我们研究了一个复值数据的例子，其中实部和虚部通过非圆特性在统计上是相关的。在这种情况下，完全连接的前馈CVNN的性能进行比较，对一个实值等效模型。结果表明，CVNN表现更好的各种体系结构和数据结构。与实值神经网络（RVNN）相比，CVNN的准确性在统计学上具有更高的平均值和中位数以及更低的方差。此外，如果不使用正则化技术，CVNN表现出较低的过拟合。第二个贡献是使用Tensorflow作为后端发布了一个Python库（Barrachina 2019），该库支持CVNN的实现和训练，希望能够激励对该领域的进一步研究。
英文摘要：
The contributions of this paper are twofold. First, we show the potential interest of Complex-Valued Neural Network (CVNN) on classification tasks for complex-valued datasets. To highlight this assertion, we investigate an example of complex-valued data in which the real and imaginary parts are statistically dependent through the property of non-circularity. In this context, the performance of fully connected feed-forward CVNNs is compared against a real-valued equivalent model. The results show that CVNN performs better for a wide variety of architectures and data structures. CVNN accuracy presents a statistically higher mean and median and lower variance than Real-Valued Neural Network (RVNN). Furthermore, if no regularization technique is used, CVNN exhibits lower overfitting. The second contribution is the release of a Python library (Barrachina 2019) using Tensorflow as back-end that enables the implementation and training of CVNNs in the hopes of motivating further research on this area.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
