Cost-efficient deep learning method for mass inverse design of photonic devices
Résumé
We apply an efficient inverse design methodology to conceive metasurface-based beam deflectors. We start by creating a small dataset composed by the results of simple simulations to train two deep neural networks. Once the models are trained, various beam deflectors can be inverse designed without further full-wave simulations. Our approach combines physical intuition about blazed gratings with a state-of-theart optimization methodology, achieving high efficiencies while requiring modest computational effort. One design was successfully fabricated using sub-20 nm thermal scanning probe lithography.
Origine | Fichiers produits par l'(les) auteur(s) |
---|---|
licence |