论文标题
基于机器学习的EDFA增益模型可推广到多个物理设备
Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices
论文作者
论文摘要
我们报告了一种基于神经网络的掺杂纤维放大器（EDFA）增益模型，该模型是根据实验测量建立的。该模型显示了用于训练的相同设备（MSE $ \ leq $ 0.04 db $^2 $）和相同品牌的不同物理单位（概括MSE $ \ leq $ 0.06 db $^2 $）。
We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE $\leq$ 0.04 dB$^2$) and different physical units of the same make (generalization MSE $\leq$ 0.06 dB$^2$).
