Neural Networks for Fiber Amplifier Design Optimization using Experimental Training Sets
- Resource Type
- Conference
- Authors
- Rabbani, Hamed; Jalilpiran, Saber; LaRochelle, Sophie; Rusch, Leslie A.
- Source
- 2023 Conference on Lasers and Electro-Optics (CLEO) Lasers and Electro-Optics (CLEO), 2023 Conference on. :1-2 May, 2023
- Subject
- Photonics and Electrooptics
Optical fiber amplifiers
Training
Noise figure
Neural networks
Optical fiber networks
Lasers and electrooptics
Optical noise
- Language
We use a neural network trained from experimental cut-back measurements of a doped fiber. With fast, accurate predictions of noise figure and gain, we find optimal fiber length and pumping strategy for an amplified link.