Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data

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 stat...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jose Agustin Barrachina, Ren, Chenfang, Morisseau, Christele, Vieillard, Gilles, Jean-Philippe Ovarlez
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 13.04.2021
Subjects
Classification
Data structures
Neural networks
Regularization
Task complexity
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422