Training deep neural networks for the inverse design of nanophotonic structures
Abstract
Data inconsistency leads to a slow training process when deep neural networks are used for the inverse design of photonic devices, an issue that arises from the fundamental property of non-uniqueness in all inverse scattering problems. Here we show that by combining forward modeling and inverse design in a tandem architecture, one can overcome this fundamental issue, allowing deep neural networks to be effectively trained by data sets that contain non-unique electromagnetic scattering instances. This paves the way for using deep neural networks to design complex photonic structures that requires large training sets.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2017
- DOI:
- 10.48550/arXiv.1710.04724
- arXiv:
- arXiv:1710.04724
- Bibcode:
- 2017arXiv171004724L
- Keywords:
-
- Physics - Optics;
- Physics - Applied Physics
- E-Print:
- doi:10.1021/acsphotonics.7b01377