EUVIMEDEUVIMED entdecken
Crossref

Improved spectral filtering of broadband diffractive neural network by loss function engineering

Bolin Li, Guangrui Luan, Yinfei Zhu, Jinlei Fei, Min Gu, Jian Lin

Applied Physics Letters · 01.02.2025 · 126 (8)

DOI: 10.1063/5.0257384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Physics Letters, online erschienen am 26.02.2025. Verfasst von Bolin Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Shanghai Municipal Science and Technology Major Project, Science and Technology Commission of Shanghai Municipality, Shanghai Frontiers Science Center Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We engineer the loss function by removing the conventional physics-based energy constraint during the training of broadband diffractive neural networks (DNNs) to enhance their spectral filtering capabilities of supercontinuum light. Simulations show that compared to DNNs trained with conventional loss function, the suppression of out-of-band spectral intensities can be improved by three orders of magnitude, resulting in an extinction coefficient of 10−6. Additionally, the spectral resolution can be enhanced by over 50% with a 6.6% improvement of energy efficiency. These findings are corroborated by experiments conducted with a two-layer DNN. The proposed method holds promise for enhancing the performance of broadband DNNs across various applications, including spectral reconstruction, spectrum classification, and color image processing, among others.

Förderung

  • Shanghai Municipal Science and Technology Major Project
  • Science and Technology Commission of Shanghai Municipality
  • Shanghai Frontiers Science Center Program
  • National Natural Science Foundation of China

Zitieren

APA

Li, B., Luan, G., Zhu, Y., Fei, J., Gu, M., & Lin, J. (2025). Improved spectral filtering of broadband diffractive neural network by loss function engineering. Applied Physics Letters, 126(8). https://doi.org/10.1063/5.0257384

Vancouver

Li B, Luan G, Zhu Y, Fei J, Gu M, Lin J. Improved spectral filtering of broadband diffractive neural network by loss function engineering. Applied Physics Letters. 2025;126(8). doi:10.1063/5.0257384

BibTeX
@article{Li2025,
  author = {Li, Bolin and Luan, Guangrui and Zhu, Yinfei and Fei, Jinlei and Gu, Min and Lin, Jian},
  title = {Improved spectral filtering of broadband diffractive neural network by loss function engineering},
  journal = {Applied Physics Letters},
  year = {2025},
  volume = {126},
  number = {8},
  doi = {10.1063/5.0257384}
}
Kostenlos starten →