Language selection

Government of Canada / Gouvernement du Canada

Search

Pre-fabrication performance verification of a topologically optimized mode demultiplexer using deep neural networks

From National Research Council Canada

AuthorSearch for: ; Search for: ; Search for: 1; Search for: 2; Search for:
Affiliation
  1. National Research Council of Canada. Advanced Electronics and Photonics
  2. National Research Council of Canada. Digital Technologies
FormatText, Article
Conference2022 European Conference on Optical Communication (ECOC), September 18-22, 2022, Basel, Switzerland
Subjectperformance evaluation; optical design; optical device fabrication; neural networks; europe; optical computing; predictive models
Abstract
Photonics miniaturization benefits from topological inverse design that favours the use of small, difficult-to-fabricate features. We use machine learning to predict the fabrication of a topologically optimized mode demultiplexer, then re-simulate and validate its optical performance for cost-efficient pre-selection of design prior to fabrication.
Publication date
PublisherIEEE
In
  • 2022 European Conference on Optical Communication (ECOC), We5.14 (20 December 2022).
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier53dfaf84-5a42-4858-b669-ec9d76541f5e
Record created2023-05-15
Record modified2023-05-16
Date modified: