Pre-Fabrication Performance Verification of a Topologically Optimized Mode Demultiplexer Using Deep Neural Networks
- Resource Type
- Conference
- Authors
- Gostimirovic, Dusan; Masnad, Md Mahadi; Xu, Dan-Xia; Grinberg, Yuri; Liboiron-Ladouceur, Odile
- Source
- 2022 European Conference on Optical Communication (ECOC) Optical Communication (ECOC), 2022 European Conference on. :1-4 Sep, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Photonics and Electrooptics
Signal Processing and Analysis
Performance evaluation
Optical design
Optical device fabrication
Neural networks
Europe
Optical computing
Predictive models
- Language
Photonics miniaturization benefits from topological inverse design that favours the use of small, difficult-to-fabricate features. We use machine learning to predict the fabrication of a topologically optimized mode demultiplexer, then re-simulate and validate its optical performance for cost-efficient pre-selection of design prior to fabrication.