Deep Learning Accelerated Multi-Objective Optimization for Highly Performant and Mechanically Robust Nanophotonic Devices

Research output: Contribution to journalConference articlepeer-review


Deep Learning has proven successful in accelerating electromagnetic simulations of complex structures thus greatly reducing the computational burden of inverse-design problems. Exploiting this acceleration allows for exhaustive sensitivity analysis of candidate designs that would otherwise be intractable to perform. When combined with multiobjective optimization, this enables a framework where meta-device performance and robustness to fabrication uncertainties can be simultaneously optimized.

Original languageEnglish (US)
Pages (from-to)1144-1145
Number of pages2
JournalInternational Conference on Metamaterials, Photonic Crystals and Plasmonics
StatePublished - 2022
Event12th International Conference on Metamaterials, Photonic Crystals and Plasmonics, META 2022 - Torremolinos, Spain
Duration: Jul 19 2022Jul 22 2022

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Materials Science (miscellaneous)
  • Electronic, Optical and Magnetic Materials
  • Materials Chemistry

Cite this