Machine Learning for Exotic Metasurfaces

Yang Deng, Simiao Ren, Kebin Fan, Jordan M. Malof, Willie J. Padilla

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We introduce one deep neural network and an inverse method called neural adjoint method to solve high-dimensional metasurface inverse design problem. We find that, even when the solution is outside the geometry space, the neural adjoint method is still able to find a metasurface design with low error.

Original languageEnglish
Title of host publication2020 45th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2020
PublisherIEEE Computer Society
Pages25
Number of pages1
ISBN (Electronic)9781728166209
DOIs
StatePublished - Nov 8 2020
Event45th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2020 - Virtual, Buffalo, United States
Duration: Nov 8 2020Nov 13 2020

Publication series

NameInternational Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
Volume2020-November
ISSN (Print)2162-2027
ISSN (Electronic)2162-2035

Conference

Conference45th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2020
Country/TerritoryUnited States
CityVirtual, Buffalo
Period11/8/2011/13/20

Fingerprint

Dive into the research topics of 'Machine Learning for Exotic Metasurfaces'. Together they form a unique fingerprint.

Cite this