Skip to Main content Skip to Navigation
Preprints, Working 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.
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal-centralesupelec.archives-ouvertes.fr/hal-02941957
Contributor : J Agustin Barrachina <>
Submitted on : Thursday, September 17, 2020 - 2:37:16 PM
Last modification on : Tuesday, October 13, 2020 - 12:12:02 PM

File

IAAI2021_preprint.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02941957, version 1

Citation

J Agustin Barrachina, Chengfang Ren, Christele Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez. Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data. 2020. ⟨hal-02941957⟩

Share

Metrics

Record views

13

Files downloads

9