All-optical classification using a compact single-layer dual-wavelength differential diffractive network
Optics Express · 23.03.2026 · 34 (6) · 11123
DOI: 10.1364/oe.588834 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 18.03.2026. Verfasst von Haoyu Wang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Laser Fusion Research Center, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Diffractive deep neuron networks ( D 2 NNs ), which compute with photons instead of electrons, hold the potential to accelerate the advancement of artificial intelligence by delivering orders-of-magnitude improvements in computational speed, massive parallelism, and ultralow energy consumption. However, conventional multi-layer D 2 NNs are fundamentally limited by inter-layer misalignments, which increase optical architecture complexity and critically impair performance, especially at visible wavelengths where optical inter-layer alignment is highly sensitive. Here, we demonstrate a compact, single-layer dual-wavelength differential D 2 NNs that combines wavelength multiplexing and differential detection, achieving high classification accuracy with only a single diffractive modulation layer and effectively mitigating inter-layer mechanical alignment errors. By harnessing complementary spatial-frequency information encoded at two distinct wavelengths, the network effectively circumvents the intrinsic non-negativity constraint imposed by intensity-only optical detection. Numerical results demonstrate high classification accuracies of 98.59% on MNIST and 90.4% on Fashion-MNIST using only 40k tunable parameters, demonstrating improved performance compared with conventional five-layer cascaded D 2 NNs operating under single-wavelength illumination, which achieve 91.33% and 83.67% accuracy, respectively, despite utilizing 200k trainable parameters. In addition, we further demonstrate that the proposed method maintains robust performance, achieving 97.95% accuracy on MNIST and 88.7% on Fashion-MNIST, even when the number of trainable parameters is reduced to just 10k, and exhibits superior resilience against random phase perturbations. Compared with conventional multi-layer cascaded D 2 NNs operating under single-wavelength illumination, this compact single-layer design scheme not only outperforms cascaded D 2 NNs with single wavelength in classification accuracy, but also alleviates the performance degradation caused by the inter-layer mechanical misalignment, thereby offering a more robust and scalable framework for practical photonic computation applications.
Förderung
- National Natural Science Foundation of China
- Laser Fusion Research Center
- China Postdoctoral Science Foundation
Zitieren
APA
Wang, H., Li, Y., Zhu, Y., Luo, G., Li, J., Ji, Z., Zheng, H., Wang, D., Geng, Y., & Fu, T. (2026). All-optical classification using a compact single-layer dual-wavelength differential diffractive network. Optics Express, 34(6), 11123. https://doi.org/10.1364/oe.588834
Vancouver
Wang H, Li Y, Zhu Y, Luo G, Li J, Ji Z, et al. All-optical classification using a compact single-layer dual-wavelength differential diffractive network. Optics Express. 2026;34(6):11123. doi:10.1364/oe.588834
BibTeX
@article{Wang2026,
author = {Wang, Haoyu and Li, Yuhai and Zhu, Yanmin and Luo, Gang and Li, Jiacheng and Ji, Zhengrui and Zheng, Hangyu and Wang, Deen and Geng, Yuanchao and Fu, Tong},
title = {All-optical classification using a compact single-layer dual-wavelength differential diffractive network},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {6},
pages = {11123},
doi = {10.1364/oe.588834}
}
EUVIMED