论文标题
分类视角的复杂值和实价的神经网络：非圆形数据的示例
Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data
论文作者
论文摘要
本文的贡献是双重的。首先，我们展示了复杂价值神经网络（CVNN）对复杂值数据集的分类任务的潜在兴趣。为了强调这一断言，我们研究了一个复杂值数据的示例，其中实际和虚构部分在统计上取决于非圆形性的属性。在这种情况下，将完全连接的前馈CVNN的性能与实现的等效模型进行了比较。结果表明，CVNN对于各种架构和数据结构的表现更好。 CVNN的精度比实际评估的神经网络（RVNN）提出了统计学上更高的平均值，中值和差异。此外，如果不使用正则化技术，CVNN表现出较低的过度拟合。第二个贡献是使用Tensorflow作为后端发布Python图书馆（Barrachina 2019），该后端能够实施和培训CVNN，以期激励对该领域的进一步研究。
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.
