File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Nanophotonic particle simulation and inverse design using artificial neural networks

TitleNanophotonic particle simulation and inverse design using artificial neural networks
Authors
KeywordsArtificial Intelligence
Machine Learning
Nanophotonics
Scattering
Issue Date2018
Citation
Proceedings of SPIE - The International Society for Optical Engineering, 2018, v. 10526, article no. 1052607 How to Cite?
AbstractWe propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find the network needs to be trained on only a small sampling of the data in order to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used solve nanophotonic inverse design problems by using back-propogation - where the gradient is analytical, not numerical.
Persistent Identifierhttp://hdl.handle.net/10722/317062
ISSN
2023 SCImago Journal Rankings: 0.152
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorPeurifoy, John-
dc.contributor.authorShen, Yichen-
dc.contributor.authorJing, Li-
dc.contributor.authorYang, Yi-
dc.contributor.authorCano-Renteria, Fidel-
dc.contributor.authorDelacy, Brendan-
dc.contributor.authorTegmark, Max-
dc.contributor.authorJoannopoulos, John D.-
dc.contributor.authorSoljačić, Marin-
dc.date.accessioned2022-09-19T06:18:43Z-
dc.date.available2022-09-19T06:18:43Z-
dc.date.issued2018-
dc.identifier.citationProceedings of SPIE - The International Society for Optical Engineering, 2018, v. 10526, article no. 1052607-
dc.identifier.issn0277-786X-
dc.identifier.urihttp://hdl.handle.net/10722/317062-
dc.description.abstractWe propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find the network needs to be trained on only a small sampling of the data in order to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used solve nanophotonic inverse design problems by using back-propogation - where the gradient is analytical, not numerical.-
dc.languageeng-
dc.relation.ispartofProceedings of SPIE - The International Society for Optical Engineering-
dc.subjectArtificial Intelligence-
dc.subjectMachine Learning-
dc.subjectNanophotonics-
dc.subjectScattering-
dc.titleNanophotonic particle simulation and inverse design using artificial neural networks-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1117/12.2289195-
dc.identifier.scopuseid_2-s2.0-85046337326-
dc.identifier.volume10526-
dc.identifier.spagearticle no. 1052607-
dc.identifier.epagearticle no. 1052607-
dc.identifier.eissn1996-756X-
dc.identifier.isiWOS:000432479700004-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats