Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks
Computational Physics
2017-12-11 v1 Applied Physics
Optics
Abstract
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.
Keywords
Cite
@article{arxiv.1712.03222,
title = {Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks},
author = {John Peurifoy and Yichen Shen and Li Jing and Yi Yang and Fidel Cano-Renteria and Brendan Delacy and Max Tegmark and John D. Joannopoulos and Marin Soljacic},
journal= {arXiv preprint arXiv:1712.03222},
year = {2017}
}
Comments
9 pages, 5 figures in text, 3 in supplementals, work presented at FiO