Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter

Abstract

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 2.25 x 2.25 μ m2 with a 20 x 20 etched hole combination. It is the first demonstration to apply the CVAE model and the adversarial censoring for the photonics problems. 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.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Training deep neural networks for the inverse design of nanophotonic structures
• A Generative Model for Inverse Design of Metamaterials
• Interaction Networks for Learning about Objects, Relations and Physics
• Optimization of photonic crystal nanocavities based on deep learning
• Flexible Neural Representation for Physics Prediction
• Efficient and accurate inversion of multiple scattering with deep learning
• Designing Silicon Photonic Devices using Artificial Neural Networks
• Invariant Representations from Adversarially Censored Autoencoders
• Machine learning-assisted discovery of many new solid Li-ion conducting materials