Abstract
We propose a device design framework based on Bayesian optimization for efficient latent sampling of adversarial generative neural networks to expedite inverse design of tunable nanophotonic wavelength splitters. The resulting design operates at broadband telecomm-wavelengths and is electrically switchable via liquid crystal tuning.
© 2023 The Author(s)
PDF ArticleMore Like This
Minwoo Jung, Keisuke Kojima, Toshiaki Koike-Akino, Ye Wang, Dayu Zhu, and Matthew Brand
SW5E.6 CLEO: Science and Innovations (CLEO:S&I) 2022
Toshiaki Koike-Akino, Keisuke Kojima, and Ye Wang
JW3A.44 CLEO: Applications and Technology (CLEO:A&T) 2022
Keisuke Kojima, Toshiaki Koike-Akino, Yingheng Tang, and Ye Wang
IF3A.6 Integrated Photonics Research, Silicon and Nanophotonics (IPR) 2021