 |
Conference papers
Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data
Abstract : 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.
https://hal-centralesupelec.archives-ouvertes.fr/hal-03144092
Contributor : Amandine Lustrement Connect in order to contact the contributor
Submitted on : Monday, November 15, 2021 - 2:28:19 PM
Last modification on : Monday, December 13, 2021 - 9:17:26 AM
Long-term archiving on: : Wednesday, February 16, 2022 - 8:43:17 PM
Contributor : Amandine Lustrement Connect in order to contact the contributor
Submitted on : Monday, November 15, 2021 - 2:28:19 PM
Last modification on : Monday, December 13, 2021 - 9:17:26 AM
Long-term archiving on: : Wednesday, February 16, 2022 - 8:43:17 PM
File
ICASSP2021_non_circularity.pdf
Files produced by the author(s)