Reinforcement learning for photonic component design
APL Photonics · 01.10.2023 · 8 (10)
DOI: 10.1063/5.0159928 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Photonics, online erschienen am 02.10.2023. Verfasst von Donald Witt und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canada Foundation for Innovation, Natural Sciences and Engineering Research Council of Canada, British Columbia Knowledge Development Fund.
Abstract (Originalsprache)
We present a new fab-in-the-loop reinforcement learning algorithm for the design of nano-photonic components that accounts for the imperfections present in nanofabrication processes. As a demonstration of the potential of this technique, we apply it to the design of photonic crystal grating couplers fabricated on an air clad 220 nm silicon on insulator single etch platform. This fab-in-the-loop algorithm improves the insertion loss from 8.8 to 3.24 dB. The widest bandwidth designs produced using our fab-in-the-loop algorithm can cover a 150 nm bandwidth with less than 10.2 dB of loss at their lowest point.
Förderung
- Canada Foundation for Innovation
- Natural Sciences and Engineering Research Council of Canada
- British Columbia Knowledge Development Fund
Zitieren
APA
Witt, D., Young, J., & Chrostowski, L. (2023). Reinforcement learning for photonic component design. APL Photonics, 8(10). https://doi.org/10.1063/5.0159928
Vancouver
Witt D, Young J, Chrostowski L. Reinforcement learning for photonic component design. APL Photonics. 2023;8(10). doi:10.1063/5.0159928
BibTeX
@article{Witt2023,
author = {Witt, Donald and Young, Jeff and Chrostowski, Lukas},
title = {Reinforcement learning for photonic component design},
journal = {APL Photonics},
year = {2023},
volume = {8},
number = {10},
doi = {10.1063/5.0159928}
}
EUVIMED