Optical–electronic hybrid Fourier convolutional neural network based on super-pixel complex-valued modulation
Applied Optics · 10.02.2023 · 62 (5) · 1337
DOI: 10.1364/ao.478540 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, online erschienen am 07.02.2023. Verfasst von Li Fan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Huawei-ZJU Center for Innovation on Optical Computing.
Abstract (Originalsprache)
An optical–electronic hybrid convolutional neural network (CNN) system is proposed and investigated for its parallel processing capability and system design robustness. It is regarded as a practical way to implement real-time optical computing. In this paper, we propose a complex-valued modulation method based on an amplitude-only liquid-crystal-on-silicon spatial light modulator and a fixed four-level diffractive optical element. A comparison of computational results of convolutions between different modulation methods in the Fourier plane shows the feasibility of the proposed complex-valued modulation method. A hybrid CNN model with one convolutional layer of multiple channels is proposed and trained electrically for different classification tasks. Our simulation results show that this model has a classification accuracy of 97.55% for MNIST, 88.81% for Fashion MNIST, and 56.16% for Cifar10, which outperforms models using only amplitude or phase modulation and is comparable to the ideal complex-valued modulation method.
Förderung
- National Key Research and Development Program of China
- Huawei-ZJU Center for Innovation on Optical Computing
Zitieren
APA
Fan, L., Long, X., Dai, J., Li, C., Dong, X., & He, J. J. (2023). Optical–electronic hybrid Fourier convolutional neural network based on super-pixel complex-valued modulation. Applied Optics, 62(5), 1337. https://doi.org/10.1364/ao.478540
Vancouver
Fan L, Long X, Dai J, Li C, Dong X, He JJ. Optical–electronic hybrid Fourier convolutional neural network based on super-pixel complex-valued modulation. Applied Optics. 2023;62(5):1337. doi:10.1364/ao.478540
BibTeX
@article{Fan2023,
author = {Fan, Li and Long, Xilin and Dai, Jun and Li, Chong and Dong, Xiaowen and He, Jian-Jun},
title = {Optical–electronic hybrid Fourier convolutional neural network based on super-pixel complex-valued modulation},
journal = {Applied Optics},
year = {2023},
volume = {62},
number = {5},
pages = {1337},
doi = {10.1364/ao.478540}
}
EUVIMED