Recurrent diffractive deep neural networks
Optics Express · 30.12.2024 · 32 (27) · 48093
DOI: 10.1364/oe.544350 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 17.12.2024. Verfasst von Junhe Zhou und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 13 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.
Abstract (Originalsprache)
What we believe is a novel recurrent diffractive deep neural network (RD2NN) is proposed for image time division multiplexing and frequency division multiplexing. The RD2NN is formed by a diffractive deep neural network (D2NN) with its output connected backward to the input. Therefore, it enables the signals to be generated sequentially in the time domain. By precoding the images via the inverse Fourier transform (IFT), one may also realize frequency division multiplexed images. To train the RD2NN, a modified optical real-time back-propagation (BP) algorithm is proposed, which expands the RD2NN into sequential D2NNs with identical phase configurations. The temporal output images of the previous stage D2NN are used as the input image for the next stage D2NN during the training. Five consecutive images are generated either in the time domain or in the frequency domain with a 7-layer trained RD2NN.
Förderung
- National Natural Science Foundation of China
- Science and Technology Commission of Shanghai Municipality
Zitieren
APA
Zhou, J., Wang, Q., & Huang, C. (2024). Recurrent diffractive deep neural networks. Optics Express, 32(27), 48093. https://doi.org/10.1364/oe.544350
Vancouver
Zhou J, Wang Q, Huang C. Recurrent diffractive deep neural networks. Optics Express. 2024;32(27):48093. doi:10.1364/oe.544350
BibTeX
@article{Zhou2024,
author = {Zhou, Junhe and Wang, Qiqi and Huang, Chenweng},
title = {Recurrent diffractive deep neural networks},
journal = {Optics Express},
year = {2024},
volume = {32},
number = {27},
pages = {48093},
doi = {10.1364/oe.544350}
}
EUVIMED