Nanophotonic particle simulation and inverse design using artificial neural networks
© 2018 SPIE. We 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, i...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
SPIE-Intl Soc Optical Eng
2021
|
| Online Access: | https://hdl.handle.net/1721.1/132120 |
| _version_ | 1826205984616349696 |
|---|---|
| author | Cano-Renteria, Fidel Tegmark, Max Soljacic, Marin Joannopoulos, John D. Peurifoy, John Shen, Yichen Jing, Li Yang, Yi DeLacy, Brendan G. |
| author_facet | Cano-Renteria, Fidel Tegmark, Max Soljacic, Marin Joannopoulos, John D. Peurifoy, John Shen, Yichen Jing, Li Yang, Yi DeLacy, Brendan G. |
| author_sort | Cano-Renteria, Fidel |
| collection | MIT |
| description | © 2018 SPIE. We 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. |
| first_indexed | 2024-09-23T13:22:10Z |
| format | Article |
| id | mit-1721.1/132120 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T13:22:10Z |
| publishDate | 2021 |
| publisher | SPIE-Intl Soc Optical Eng |
| record_format | dspace |
| spelling | mit-1721.1/1321202022-03-29T20:51:31Z Nanophotonic particle simulation and inverse design using artificial neural networks Cano-Renteria, Fidel Tegmark, Max Soljacic, Marin Joannopoulos, John D. Peurifoy, John Shen, Yichen Jing, Li Yang, Yi DeLacy, Brendan G. © 2018 SPIE. We 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. 2021-09-20T18:21:05Z 2021-09-20T18:21:05Z 2019-03-28T17:13:35Z Article http://purl.org/eprint/type/ConferencePaper 9781510615373 9781510615380 https://hdl.handle.net/1721.1/132120 Cano-Renteria, Fidel, Max Tegmark, Marin Soljacic, John D. Joannopoulos, John Peurifoy, Yichen Shen, Li Jing, Yi Yang, and Brendan G. DeLacy. “Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks.” Edited by Marek Osiński, Yasuhiko Arakawa, and Bernd Witzigmann. Physics and Simulation of Optoelectronic Devices XXVI (February 23, 2018). doi:10.1117/12.2289195. http://dx.doi.org/10.1117/12.2289195 Physics and Simulation of Optoelectronic Devices XXVI Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf SPIE-Intl Soc Optical Eng SPIE |
| spellingShingle | Cano-Renteria, Fidel Tegmark, Max Soljacic, Marin Joannopoulos, John D. Peurifoy, John Shen, Yichen Jing, Li Yang, Yi DeLacy, Brendan G. Nanophotonic particle simulation and inverse design using artificial neural networks |
| title | Nanophotonic particle simulation and inverse design using artificial neural networks |
| title_full | Nanophotonic particle simulation and inverse design using artificial neural networks |
| title_fullStr | Nanophotonic particle simulation and inverse design using artificial neural networks |
| title_full_unstemmed | Nanophotonic particle simulation and inverse design using artificial neural networks |
| title_short | Nanophotonic particle simulation and inverse design using artificial neural networks |
| title_sort | nanophotonic particle simulation and inverse design using artificial neural networks |
| url | https://hdl.handle.net/1721.1/132120 |
| work_keys_str_mv | AT canorenteriafidel nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT tegmarkmax nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT soljacicmarin nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT joannopoulosjohnd nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT peurifoyjohn nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT shenyichen nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT jingli nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT yangyi nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks AT delacybrendang nanophotonicparticlesimulationandinversedesignusingartificialneuralnetworks |