TR2020-026

Deep Neural Network Inverse Design of Integrated Nanophotonic Devices



We propose a novel Conditional Variational Autoencoder (CVAE) model, enhanced with adversarial censoring and active learning, for the generation of 550 nm broad bandwidth (1250 nm to 1800 nm) power splitters with arbitrary splitting ratio. The device footprint is 2.25x2.25 um2 with a 20x20 etched hole combination. It is the first demonstration to apply the CVAE model for assisting the silicon photonics device design. We confirm that the optimized device has an overall performance close to 90% across all bandwidths from 1250 nm to 1800 nm. To the best of our knowledge, this is the smallest broadband power splitter with arbitrary ratio.