Optical Fourier convolutional neural network with high efficiency in image classification
Optics Express · 17.06.2024 · 32 (13) · 23575
DOI: 10.1364/oe.522842 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 12.06.2024. Verfasst von Yan Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 25 Literaturangaben.
Abstract (Originalsprache)
Compared to traditional neural networks, optical neural networks demonstrate significant advantages in terms of information processing speed, energy efficiency, anti-interference capability, and scalability. Despite the rapid development of optical neural networks in recent years, most existing systems still face challenges such as complex structures, time-consuming training, and insufficient accuracy. This study fully leverages the coherence of optical systems and introduces an optical Fourier convolutional neural network based on the diffraction of complex image light fields. This new network is not only structurally simple and fast in computation but also excels in image classification accuracy. Our research opens new perspectives for the development of optical neural networks, and also offers insights for future applications in high-efficiency, low-energy-consumption computing domains.
Zitieren
APA
Liu, Y., Qin, J., Liu, Y., Liu, Y., Liu, X., Ye, F., & Li, W. (2024). Optical Fourier convolutional neural network with high efficiency in image classification. Optics Express, 32(13), 23575. https://doi.org/10.1364/oe.522842
Vancouver
Liu Y, Qin J, Liu Y, Liu Y, Liu X, Ye F, et al. Optical Fourier convolutional neural network with high efficiency in image classification. Optics Express. 2024;32(13):23575. doi:10.1364/oe.522842
BibTeX
@article{Liu2024,
author = {Liu, Yan and Qin, Jianwei and Liu, Yanbing and Liu, Yuanan and Liu, Xun and Ye, Fangwei and Li, Wei},
title = {Optical Fourier convolutional neural network with high efficiency in image classification},
journal = {Optics Express},
year = {2024},
volume = {32},
number = {13},
pages = {23575},
doi = {10.1364/oe.522842}
}
EUVIMED