Abstract
We train a convolutional neural network (CNN) that can predict the optical response of randomly generated nanopatterned photonic power splitters in a 2400 design space with a prediction correlation coefficient of 85 %.
© 2019 The Author(s)
PDF ArticleMore Like This
Mohammad H. Tahersima, Keisuke Kojima, Toshiaki Koike-Akino, Devesh Jha, Bingnan Wang, Chungwei Lin, and Kieran Parsons
W3B.5 Optical Fiber Communication Conference (OFC) 2019
Jianjun Hao, Lei Zheng, Daquan Yang, and Yijun Guo
M4A.296 Asia Communications and Photonics Conference (ACP) 2019
Nicola Peserico, Hangbo Yang, Xiaoxuan Ma, Shurui Li, Mostafa Hosseini, Jonathan K. George, Puneet Gupta, Chee Wei Wong, and Volker J. Sorger
ITh3D.7 Imaging Systems and Applications (IS) 2022