EUVIMEDEUVIMED entdecken
Open Access

Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission

Yitong Chen iD, Tiankuang Zhou iD, Jiamin Wu iD, Hui Qiao iD, Xing Lin iD, Lu Fang iD, Qionghai Dai iD

Science Advances · 17.02.2023 · 9 (7)

DOI: 10.1126/sciadv.adf8437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 17.02.2023. Verfasst von Yitong Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automation, Tsinghua University, Beijing 100084, China. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Following the explosive growth of global data, there is an ever-increasing demand for high-throughput processing in image transmission systems. However, existing methods mainly rely on electronic circuits, which severely limits the transmission throughput. Here, we propose an end-to-end all-optical variational autoencoder, named photonic encoder-decoder (PED), which maps the physical system of image transmission into an optical generative neural network. By modeling the transmission noises as the variation in optical latent space, the PED establishes a large-scale high-throughput unsupervised optical computing framework that integrates main computations in image transmission, including compression, encryption, and error correction to the optical domain. It reduces the system latency of computation by more than four orders of magnitude compared with the state-of-the-art devices and transmission error ratio by 57% than on-off keying. Our work points to the direction for a wide range of artificial intelligence–based physical system designs and next-generation communications.

Autor:innen und Institutionen

  • Department of Automation, Tsinghua University, Beijing 100084, China.
  • Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing 100084, China.
  • Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China.
  • Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.

ORCID-Profile: Yitong Chen, Tiankuang Zhou, Jiamin Wu, Hui Qiao, Xing Lin, Lu Fang, Qionghai Dai

Zitieren

APA

Chen, Y., Zhou, T., Wu, J., Qiao, H., Lin, X., Fang, L., & Dai, Q. (2023). Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission. Science Advances, 9(7). https://doi.org/10.1126/sciadv.adf8437

Vancouver

Chen Y, Zhou T, Wu J, Qiao H, Lin X, Fang L, et al. Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission. Science Advances. 2023;9(7). doi:10.1126/sciadv.adf8437

BibTeX
@article{Chen2023,
  author = {Chen, Yitong and Zhou, Tiankuang and Wu, Jiamin and Qiao, Hui and Lin, Xing and Fang, Lu and Dai, Qionghai},
  title = {Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission},
  journal = {Science Advances},
  year = {2023},
  volume = {9},
  number = {7},
  doi = {10.1126/sciadv.adf8437}
}
Kostenlos starten →