Mapping the global design space of nanophotonic components using machine learning pattern recognition
Machine learning is increasingly used in nanophotonics for designing novel classes of complex devices but the general parameter behavior is often neglected. Here, the authors report a new methodology to discover and visualize optimal design spaces with respect to multiple performance objectives.
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2019-10-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-019-12698-1 |