Abstract
We demonstrate a tandem neural network architecture that tolerates inconsistent training instances in inverse design of nanophotonic devices. It provides a way to train large neural networks for the inverse design of complex photonic structures.
© 2019 The Author(s)
PDF ArticleMore Like This
Rohit Unni, Kan Yao, and Yuebing Zheng
JW2D.14 CLEO: Applications and Technology (CLEO:A&T) 2020
Jianjun Hao, Lei Zheng, Daquan Yang, and Yijun Guo
M4A.296 Asia Communications and Photonics Conference (ACP) 2019
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