Abstract
Instead of using FDTD simulations for all the inverse design steps, we proposed to use neural network-based fitting to estimate the output of the FDTD simulations, and improve the design. We observed clear acceleration in the improvement of metric.
© 2017 Optical Society of America
PDF ArticleMore Like This
John Peurifoy, Yichen Shen, Yi Yang, Li Jing, Fidel Cano-Renteria, John Joannopoulos, Max Tegmark, and Marin Soljačić
FTh4A.4 Frontiers in Optics (FiO) 2017
Keisuke Kojima, Toshiaki Koike-Akino, Yingheng Tang, and Ye Wang
IF3A.6 Integrated Photonics Research, Silicon and Nanophotonics (IPR) 2021
Ayan Sinha, Justin Lee, Shuai Li, and George Barbastathis
W1A.3 Digital Holography and Three-Dimensional Imaging (DH) 2017