Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data
| Autor: | C. Morisseau, Jean-Philippe Ovarlez, G. Vieillard, Jose Agustin Barrachina, Chengfang Ren |
|---|---|
| Přispěvatelé: | DEMR, ONERA, Université Paris Saclay [Palaiseau], ONERA-Université Paris-Saclay, Sondra, CentraleSupélec, Université Paris-Saclay (SONDRA), ONERA-CentraleSupélec-Université Paris-Saclay |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Synthetic aperture radar
FOS: Computer and information sciences Computer Science - Machine Learning Computer science Property (programming) Context (language use) Machine Learning (stat.ML) 02 engineering and technology Overfitting law.invention Machine Learning (cs.LG) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Statistics - Machine Learning law Radar imaging 0202 electrical engineering electronic engineering information engineering Sensitivity (control systems) Radar Artificial neural network business.industry Pattern recognition [SPI.TRON]Engineering Sciences [physics]/Electronics 020201 artificial intelligence & image processing Artificial intelligence business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
| Zdroj: | 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, Canada HAL ICASSP |
| Popis: | 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. Comment: 6 pages, 5 figures, conference, preprint |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|