EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity

Ziang Yin, Qi Jing, Raktim Sarma, Rena Huang, Yu Yao, Jiaqi Gu

ACM Transactions on Design Automation of Electronic Systems · 31.03.2027 · 32 (2) · 1-19

DOI: 10.1145/3840398 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 13.11.2026. Verfasst von Ziang Yin und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffractive optical neural networks (DONNs) have demonstrated unparalleled energy efficiency and parallelism by processing information directly in the optical domain. However, their computational expressivity is constrained by static, passive diffractive phase masks that lack efficient nonlinear responses and reprogrammability. To address these limitations, we introduce Recurrent Diffractive Optical Neural Processor ( ReDON ), a novel architecture featuring reconfigurable, recurrent self-modulated nonlinearity. This mechanism enables dynamic, input-dependent optical transmission through in-situ electro-optic self-modulation, providing a highly efficient and reprogrammable approach to optical computation. Inspired by the gated linear unit (GLU) in large language models, ReDON senses a fraction of the propagating optical field and modulates its phase or intensity via a lightweight, parametric function, enabling effective nonlinearity with minimal inference overhead. As a non-von Neumann architecture with the main weighting units (metasurfaces) being fixed, we substantially extend the DONN’s nonlinear representational capacity and task adaptability via recurrent optical hardware reuse and dynamically tunable nonlinearity. We systematically investigate various self-modulation configurations to uncover the tradeoffs between hardware efficiency and expressivity. On image recognition and segmentation tasks, ReDON improves test accuracy and mIoU by up to 20% over prior DONNs with optical or digital nonlinearities at comparable complexity and negligible power overhead. This work establishes a new paradigm for reconfigurable nonlinear optical computing, uniting the benefits of recurrence and self-modulation in non-von Neumann analog processors.

Zitieren

APA

Yin, Z., Jing, Q., Sarma, R., Huang, R., Yao, Y., & Gu, J. (2027). ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity. ACM Transactions on Design Automation of Electronic Systems, 32(2), 1-19. https://doi.org/10.1145/3840398

Vancouver

Yin Z, Jing Q, Sarma R, Huang R, Yao Y, Gu J. ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity. ACM Transactions on Design Automation of Electronic Systems. 2027;32(2):1-19. doi:10.1145/3840398

BibTeX
@article{Yin2027,
  author = {Yin, Ziang and Jing, Qi and Sarma, Raktim and Huang, Rena and Yao, Yu and Gu, Jiaqi},
  title = {ReDON: Recurrent Diffractive Optical Neural Processor with Reconfigurable Self-Modulated Nonlinearity},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2027},
  volume = {32},
  number = {2},
  pages = {1--19},
  doi = {10.1145/3840398}
}
Kostenlos starten →