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

Deep learning to accelerate Maxwell’s equations for inverse design of dielectric metasurfaces

Not Accessible

Your library or personal account may give you access

Abstract

We present a data-driven forward simulation framework for the inverse design of metasurfaces that is more accurate than methods based on the local phase approximation, a factor of 104 times faster than mesh based solvers.

© 2021 The Author(s)

PDF Article
More Like This
Deep Learning enabled Forward Modeling and Inverse Design of Integrated Nanophotonic Gratings

Hussaina Ali Akbar, Anusha Rehman, Zeeshan Karim, Ahmad Usman, and Syed Hasan Asim
JTh5A.100 Frontiers in Optics (FiO) 2021

Deep Learning based Inverse Design of Integrated Silicon Nanophotonic Gratings

Hussaina Ali Akbar, Anusha Rehman, Zeeshan Karim, Ahmad Usman, and Syed Hasan Asim
jsiv_p_1 European Quantum Electronics Conference (EQEC) 2021

On the Use of Deep Learning for Lens Design

Geoffroi Côté, Jean-François Lalonde, and Simon Thibault
120781A International Optical Design Conference (IODC) 2021

Poster Presentation

Media 1: PDF (1109 KB)     
Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved