Diffractive neural networks with improved expressive power for gray-scale image classification
Photonics Research · 01.06.2024 · 12 (6) · 1159
DOI: 10.1364/prj.513845 ↗Kurz gefasst
Fachartikel in der Zeitschrift Photonics Research, online erschienen am 27.05.2024. Verfasst von Minjia Zheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Major Program of National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality, National Key Research and Development Program of China.
Abstract (Originalsprache)
In order to harness diffractive neural networks (DNNs) for tasks that better align with real-world computer vision requirements, the incorporation of gray scale is essential. Currently, DNNs are not powerful enough to accomplish gray-scale image processing tasks due to limitations in their expressive power. In our work, we elucidate the relationship between the improvement in the expressive power of DNNs and the increase in the number of phase modulation layers, as well as the optimization of the Fresnel number, which can describe the diffraction process. To demonstrate this point, we numerically trained a double-layer DNN, addressing the prerequisites for intensity-based gray-scale image processing. Furthermore, we experimentally constructed this double-layer DNN based on digital micromirror devices and spatial light modulators, achieving eight-level intensity-based gray-scale image classification for the MNIST and Fashion-MNIST data sets. This optical system achieved the maximum accuracies of 95.10% and 80.61%, respectively.
Förderung
- Major Program of National Natural Science Foundation of China
- Science and Technology Commission of Shanghai Municipality
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Zheng, M., Liu, W., Shi, L., & Zi, J. (2024). Diffractive neural networks with improved expressive power for gray-scale image classification. Photonics Research, 12(6), 1159. https://doi.org/10.1364/prj.513845
Vancouver
Zheng M, Liu W, Shi L, Zi J. Diffractive neural networks with improved expressive power for gray-scale image classification. Photonics Research. 2024;12(6):1159. doi:10.1364/prj.513845
BibTeX
@article{Zheng2024,
author = {Zheng, Minjia and Liu, Wenzhe and Shi, Lei and Zi, Jian},
title = {Diffractive neural networks with improved expressive power for gray-scale image classification},
journal = {Photonics Research},
year = {2024},
volume = {12},
number = {6},
pages = {1159},
doi = {10.1364/prj.513845}
}
EUVIMED