We present three different approaches to apply deep learning to inverse design for nanophotonic devices. The forward models use device parameters as inputs and device responses as outputs. This model works as a fast approximation method which can be integrated in the optimization loop, and can accelerate the optimization. The network is updated as we obtain more simulation data on the fly for better approximation. The inverse modeling uses a network trained with the device responses as inputs, and the device parameters as outputs. This way the network outputs the device structure given the target optical response. This network can also be updated as we obtain more data during the optimization and validation. The generative model we use is a variant of a conditional variational autoencoder, and the network learns the statistical characteristics of the device structure, and it generates a series of improved designs given the target device responses. By using these three models, we demonstrate how to design nanophotonic power splitters with multiple splitting ratios.

Date Published: 5 March 2021
PDF: 10 pages
Proc. SPIE 11703, AI and Optical Data Sciences II, 117030V (5 March 2021); doi: 10.1117/12.2579104

Published in SPIE Proceedings Vol. 11703:
AI and Optical Data Sciences II
Bahram Jalali; Ken-ichi Kitayama, Editor(s)