Inverse design of an on-chip optical response predictor enabled by a deep neural network.
Opt Express
; 31(2): 2049-2060, 2023 Jan 16.
Article
em En
| MEDLINE
| ID: mdl-36785227
ABSTRACT
We proposed inverse-designed nanophotonic waveguide devices which have the desired optical responses in the wide band of 1450-1650â
nm. The proposed devices have an ultra-compact size of just 1.5â
µm × 3.0â
µm and are designed on a silicon-on-insulator (SOI) waveguide platform. Individual nano-pixels with dimensions of 150â
nm × 150â
nm were made of either silicon or silicon dioxide, and the materials for the 200 total cells were determined using a trained deep neural network. While training the two networks, the hyperparameter optimization method was applied to make the training process efficient. We then fabricated the proposed devices using a CMOS-compatible fabrication process, and experimentally verified the fabricated device performance.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Ano de publicação:
2023
Tipo de documento:
Article