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.
© 2022 The Author(s)
PDF ArticleMore Like This
Timo Gahlmann and Philippe Tassin
NoM3C.4 Novel Optical Materials and Applications (NOMA) 2022
Vinod Bajaj, Mathieu Chagnon, Sander Wahls, and Vahid Aref
M1H.3 Optical Fiber Communication Conference (OFC) 2022
Vinod Bajaj, Vahid Aref, and Sander Wahls
Th2C.1 European Conference and Exhibition on Optical Communication (ECOC) 2022