SPDec 7, 2022
FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip TrainingKeren Liu, Erik Börjeson, Christian Häger et al.
We design and implement an adaptive machine learning equalizer that alternates multiple linear and nonlinear computational layers on an FPGA. On-chip training via gradient backpropagation is shown to allow for real-time adaptation to time-varying channel impairments.
ITJun 19, 2018
ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion FiltersChristoffer Fougstedt, Christian Häger, Lars Svensson et al.
We consider time-domain digital backpropagation with chromatic dispersion filters jointly optimized and quantized using machine-learning techniques. Compared to the baseline implementations, we show improved BER performance and >40% power dissipation reductions in 28-nm CMOS.