Abstract
We show that a modified CGAN machine learning method that balances the accuracy of desired optical properties with experimental feasibility can solve the free-form inverse design of nanophotonic matasurfaces.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Timo Gahlmann and Philippe Tassin
FM5H.7 CLEO: QELS_Fundamental Science (CLEO:FS) 2022
Dusan Gostimirovic, Md Mahadi Masnad, Dan-Xia Xu, Yuri Grinberg, and Odile Liboiron-Ladouceur
We5.14 European Conference and Exhibition on Optical Communication (ECOC) 2022
Jonathan A. Fan
AM4K.4 CLEO: Applications and Technology (CLEO:A&T) 2019