EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multitask Diffractive Deep Neural Networks Enabled by Joint Distance–Frequency Encoding

Zhengxuan Jiang iD, Zongmao Fei, Wen Jiang, Guowen Ding iD, Ke Chen iD, Yijun Feng iD

Nanophotonics · 12.11.2026 · 15 (21)

DOI: 10.1002/nap2.70342 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nanophotonics, online erschienen am 30.10.2026. Verfasst von Zhengxuan Jiang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research Center of Applied Electromagnetics Nanjing University of Information Science and Technology Nanjing China. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffractive deep neural networks (D 2 NNs) offer a promising route toward high‐speed wave‐based computing, but most existing architectures are restricted to a single fixed function, whereas multitask implementations often require additional hardware complexity. Here, a multitask D 2 NN architecture based on joint distance and frequency encoding is proposed and demonstrated. The interlayer distance is introduced as a physically reconfigurable task‐encoding dimension and is combined with a dual‐frequency phase‐independent metasurface to enable task multiplexing within a single passive hardware system. Scalar diffraction simulations on the corresponding testing datasets yielded accuracies of 99.7% for 9‐class orbital angular momentum (OAM) classification, 86.4% for 9‐class direction recognition, 98.8% for 4‐category programmable logic‐gate operations, and 95.4% for 4‐class MNIST digit recognition (Digits 0–3). Full‐wave electromagnetic simulations further support the physical feasibility of the designed metasurface implementation, whereas microwave measurements on selected representative inputs provide proof‐of‐concept evidence of task‐dependent energy routing and distance‐enabled task switching. This joint‐encoding strategy provides a compact and resource‐efficient route for multifunctional intelligent wave‐based computing systems.

Schlagwörter

Stichwörter der Autor:innen

diffractive neural networksdistance–frequency encodingmetasurfacesmicrowave computingmulti‐task learning

Autor:innen und Institutionen

  • Research Center of Applied Electromagnetics Nanjing University of Information Science and Technology Nanjing China.
  • School of Electronic Science and Engineering Nanjing University Nanjing China.

ORCID-Profile: Zhengxuan Jiang, Guowen Ding, Ke Chen, Yijun Feng

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation

Zitieren

APA

Jiang, Z., Fei, Z., Jiang, W., Ding, G., Chen, K., & Feng, Y. (2026). Multitask Diffractive Deep Neural Networks Enabled by Joint Distance–Frequency Encoding. Nanophotonics, 15(21). https://doi.org/10.1002/nap2.70342

Vancouver

Jiang Z, Fei Z, Jiang W, Ding G, Chen K, Feng Y. Multitask Diffractive Deep Neural Networks Enabled by Joint Distance–Frequency Encoding. Nanophotonics. 2026;15(21). doi:10.1002/nap2.70342

BibTeX
@article{Jiang2026,
  author = {Jiang, Zhengxuan and Fei, Zongmao and Jiang, Wen and Ding, Guowen and Chen, Ke and Feng, Yijun},
  title = {Multitask Diffractive Deep Neural Networks Enabled by Joint Distance–Frequency Encoding},
  journal = {Nanophotonics},
  year = {2026},
  volume = {15},
  number = {21},
  doi = {10.1002/nap2.70342}
}
Kostenlos starten →