Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data
This work addresses the problem of improving classification performance for complex-valued datasets in signal processing or communications, though it is incremental as it builds on existing CVNN research.
The paper demonstrates that Complex-Valued Neural Networks (CVNNs) outperform real-valued equivalents on classification tasks with non-circular complex-valued data, showing higher accuracy, lower variance, and reduced overfitting across various architectures.
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.