TY - GEN
T1 - Machine Learning for Exotic Metasurfaces
AU - Deng, Yang
AU - Ren, Simiao
AU - Fan, Kebin
AU - Malof, Jordan M.
AU - Padilla, Willie J.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/8
Y1 - 2020/11/8
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85103169513&partnerID=8YFLogxK
U2 - 10.1109/IRMMW-THz46771.2020.9370973
DO - 10.1109/IRMMW-THz46771.2020.9370973
M3 - Conference contribution
AN - SCOPUS:85103169513
T3 - International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
SP - 25
BT - 2020 45th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2020
PB - IEEE Computer Society
T2 - 45th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2020
Y2 - 8 November 2020 through 13 November 2020
ER -