Published October 25, 2023 | Version v1
Poster Open

Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems

Authors/Creators

  • 1. ROR icon Aston University
  • 2. Infinera, Carnaxide, Portugal
  • 3. Infinera, Munich, Germany

Description

For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A "single" NN-based equalizer improves Q-factor by up to 4 dB compared to CDC, without re-training, even with variations in launch power, symbol rate, or transmission distance.

Files

ECOC_Poster_A0 Sasipim Srivallapanondh.pdf

Files (958.3 kB)

Name Size Download all
md5:a7a68b53216a51edc209634763278841
958.3 kB Preview Download

Additional details

Funding

European Commission
MENTOR - Machine LEarning in Optical NeTwORks 956713