Accelerating Electromagnetic Inverse-Design using Deep Learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

One of the primary ways that deep learning has been applied to electro magnetics in recent years is for accelerating inverse design. We present one such method for designing metasurface supercells which are robust to structural erosion and dilation, a typical variety of nanofabrication error. A pair of deep neural networks are trained to high accuracy to predict diffraction efficiencies from a supercell mask, and then evaluated exhaustively to find tolerance bounds for freeform supercell designs.

Original languageEnglish (US)
Title of host publication2022 16th European Conference on Antennas and Propagation, EuCAP 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9788831299046
StatePublished - 2022
Event16th European Conference on Antennas and Propagation, EuCAP 2022 - Madrid, Spain
Duration: Mar 27 2022Apr 1 2022

Publication series

Name2022 16th European Conference on Antennas and Propagation, EuCAP 2022

Conference

Conference16th European Conference on Antennas and Propagation, EuCAP 2022
Country/TerritorySpain
CityMadrid
Period3/27/224/1/22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Radiation

Fingerprint

Dive into the research topics of 'Accelerating Electromagnetic Inverse-Design using Deep Learning'. Together they form a unique fingerprint.

Cite this