Conference paper
Generalization Properties of Machine Learning-based Raman Models
Department of Photonics Engineering, Technical University of Denmark1
Machine Learning in Photonic Systems, Department of Photonics Engineering, Technical University of Denmark2
Centre of Excellence for Silicon Photonics for Optical Communications, Centers, Technical University of Denmark3
Polytechnic University of Turin4
Ultra-fast Optical Communication, Department of Photonics Engineering, Technical University of Denmark5
We investigate the generalization capabilities of neural network-based Raman amplifier models. The new proposed model architecture, including fiber parameters as inputs, can predict Raman gains of fiber types unseen during training, unlike previous fiber-specific models.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2021 |
Pages: | 1-3 |
Proceedings: | 2021 Optical Fiber Communications Conference and Exhibition |
ISBN: | 1665429380 , 1943580863 , 9781665429382 and 9781943580866 |
Types: | Conference paper |
ORCIDs: | De Moura, U. C. , Zibar, D. and Da Ros, F. |