Exploiting graph neural networks to perform finite-difference time-domain based optical simulations
Having an artificial neural network that solves Maxwell’s equations in a general setting is an intellectual challenge and a great utility. Recently, there have been multiple successful attempts to use artificial neural networks to predict electromagnetic fields, given a specific source and interacti...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-03-01
|
| Series: | APL Photonics |
| Online Access: | http://dx.doi.org/10.1063/5.0139004 |