Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Generating high performance, topologically-complex metasurfaces with neural networks

Not Accessible

Your library or personal account may give you access

Abstract

We show that generative neural networks, combined with topology optimization, are a computationally efficient route to producing high efficiency, topologically-complex metasurfaces across a broad operating parameter space.

© 2019 The Author(s)

PDF Article
More Like This
High efficiency metasurface design based on deep generative models

Jiaqi Jiang, David Sell, and Jonathan A. Fan
IW1A.5 Integrated Photonics Research, Silicon and Nanophotonics (IPR) 2019

Deep Neural Networks for the Topological Optimization of Metasurfaces

Timo Gahlmann and Philippe Tassin
NoM3C.4 Novel Optical Materials and Applications (NOMA) 2022

Machine-learning-assisted topology optimization for highly efficient thermal emitter design

Zhaxylyk A. Kudyshev, Alexander V. Kildishev, Vladimir M. Shalaev, and Alexandra Boltasseva
FTh3C.2 CLEO: QELS_Fundamental Science (CLEO:FS) 2019

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.