Real-Time Implementation of Machine-Learning DSP
Paper in proceeding, 2024
While ML algorithms can learn and adapt to channel characteristics, implementation of ML-based DSP hardware is challenging. We demonstrate a real-time implementation of a model-based ML equalizer that compensates a non-linear and time-varying channel.
Author
Erik Börjeson
Chalmers, Microtechnology and Nanoscience (MC2), Microwave Electronics
Keren Liu
Student at Chalmers
Christian Häger
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Per Larsson-Edefors
Chalmers, Microtechnology and Nanoscience (MC2), Microwave Electronics
2024 Optical Fiber Communications Conference and Exhibition, OFC 2024 - Proceedings
9781957171326 (ISBN)
2024 Optical Fiber Communications Conference and Exhibition
San Diego, USA,
San Diego, USA,
Physics-Based Deep Learning for Optical Data Transmission and Distributed Sensing
Swedish Research Council (VR) (2020-04718), 2021-01-01 -- 2024-12-31.
Areas of Advance
Information and Communication Technology
Subject Categories (SSIF 2011)
Communication Systems
Embedded Systems
Control Engineering
Signal Processing
DOI
10.1364/ofc.2024.th3j.1