EUVIMEDEUVIMED entdecken
Crossref

Photonic Tensor Processing Unit by Depthwise Separable Convolution

Weiwei Pan, Heng Chen, Chen Ji

IEEE Photonics Technology Letters · 2026-11 · 38 (21) · 1692-1695

DOI: 10.1109/lpt.2026.3713231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Photonics Technology Letters, 2026-11. Verfasst von Weiwei Pan und 2 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose and experimentally demonstrate a hardware-efficient photonic tensor processing unit (PTPU) enabled by depthwise separable convolution (DSC) and wavelength division multiplexing (WDM). Fabricated on an 800nm silicon nitride platform, the proposed PTPU implements a $4\times 2 \times 2\times 1$ kernel using only four microring resonators and eight Mach-Zehnder interferometers, reducing the number of photonic devices by 25% compared to standard convolution implementation. The tensor convolution capability of the PTPU is validated through image convolution tasks. Furthermore, when deployed as the convolution module in a DSC-based convolutional neural network (CNN) for NoduleMNIST 3D dataset classification, the proposed PTPU achieves 85.42% prediction accuracy, which is comparable to software-based implementations. These results establish the proposed PTPU as a highly efficient photonic neural network architecture, particularly well-suited for resource-constrained applications.

Zitieren

APA

Pan, W., Chen, H., & Ji, C. (2026). Photonic Tensor Processing Unit by Depthwise Separable Convolution. IEEE Photonics Technology Letters, 38(21), 1692-1695. https://doi.org/10.1109/lpt.2026.3713231

Vancouver

Pan W, Chen H, Ji C. Photonic Tensor Processing Unit by Depthwise Separable Convolution. IEEE Photonics Technology Letters. 2026;38(21):1692-1695. doi:10.1109/lpt.2026.3713231

BibTeX
@article{Pan2026,
  author = {Pan, Weiwei and Chen, Heng and Ji, Chen},
  title = {Photonic Tensor Processing Unit by Depthwise Separable Convolution},
  journal = {IEEE Photonics Technology Letters},
  year = {2026},
  volume = {38},
  number = {21},
  pages = {1692--1695},
  doi = {10.1109/lpt.2026.3713231}
}
Kostenlos starten →