A preemphasis-aware model for SOAs with non-flat WDM inputs yielding a root-mean-square error of less than 0.05 dB is presented. It outperforms generic neural network models while using a fraction of the training data. (C) 2022 The Author(s)
Preemphasis-Aware Semiconductor Optical Amplifier Model
Zhao, Xiaohui;
2023-01-01
Abstract
A preemphasis-aware model for SOAs with non-flat WDM inputs yielding a root-mean-square error of less than 0.05 dB is presented. It outperforms generic neural network models while using a fraction of the training data. (C) 2022 The Author(s)File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Conference [8]_OFC2023.pdf
Accesso riservato
:
Publisher’s version
Dimensione
688.08 kB
Formato
Adobe PDF
|
688.08 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
