Machine Learning for 6G Optics
Channel Equalization & Fiber Nonlinearity Mitigation (KIGLIS)
KIGLIS was a collaborative project on AI for 6G optical communications with Nokia Bell Labs and VPIphotonics, funded by the German Federal Ministry of Education and Research (BMFTR), 2022–2024.
I proposed two novel machine learning algorithms for 6G channel equalization and fiber nonlinearity mitigation, presented at the leading venues in optical communications:
- A Novel Machine Learning-Based Equalizer for a Downstream 100G PAM-4 PON (OFC 2024, oral, top 5%)
- Time-Series Forecasting Methods in Fiber Nonlinearity Mitigation (ECOC 2024, oral, top 5%)
- Time-Series Prediction Methods in Fiber Nonlinearity Mitigation (MDPI Photonics 2024, invited)