Deep Neural Networks for Designing Integrated Photonics
Keisuke Kojima, Mohammad Hossein Tahersima, Toshiaki Koike–Akino, Devesh K. Jha, Yingheng Tang, Ye Wang, Kieran Parsons, Fengqiao Sang, Jonathan Klamkin · 2020
We present two different approaches to apply deep learning to inverse design for nanophotonic devices. First, we use a regression model, with device parameters as inputs and device responses as outputs, or vice versa. Second, we use a novel generative model to create a series of improved designs. We demonstrate them to design nanophotonic power splitters with multiple splitting ratios.