Deep photonic reservoir computing recurrent network
Optica · 20.12.2023 · 10 (12) · 1745
DOI: 10.1364/optica.506635 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optica, online erschienen am 19.12.2023. Verfasst von Yi-Wei Shen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 108-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Natural Science Foundation of Shanghai, National Natural Science Foundation of China.
Abstract (Originalsprache)
Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving practical complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept PRC consisting of 4 hidden layers and a total of 320 interconnected neurons (80 neurons per layer) is demonstrated in experiment. The deep PRC is applied in solving the real-world problem of signal equalization in an optical fiber communication system. It is found that the deep PRC exhibits strong capability in compensating for the nonlinear impairment of optical fibers.
Förderung
- Natural Science Foundation of Shanghai
- National Natural Science Foundation of China
Zitieren
APA
Shen, Y., Li, R., Liu, G., Yu, J., He, X., Yi, L., & Wang, C. (2023). Deep photonic reservoir computing recurrent network. Optica, 10(12), 1745. https://doi.org/10.1364/optica.506635
Vancouver
Shen Y, Li R, Liu G, Yu J, He X, Yi L, et al. Deep photonic reservoir computing recurrent network. Optica. 2023;10(12):1745. doi:10.1364/optica.506635
BibTeX
@article{Shen2023,
author = {Shen, Yi-Wei and Li, Rui-Qian and Liu, Guan-Ting and Yu, Jingyi and He, Xuming and Yi, Lilin and Wang, Cheng},
title = {Deep photonic reservoir computing recurrent network},
journal = {Optica},
year = {2023},
volume = {10},
number = {12},
pages = {1745},
doi = {10.1364/optica.506635}
}
EUVIMED