FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training
Paper i proceeding, 2023

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.

Författare

Keren Liu

Erik Börjeson

Embedded Electronics Systems and Computer Graphics

Christian Häger

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

Per Larsson-Edefors

Embedded Electronics Systems and Computer Graphics

Optical Fiber Communication Conference, OFC 2023

Optical Fiber Communication Conference, OFC 2023
San Diego, USA,

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Kommunikationssystem

Inbäddad systemteknik

Signalbehandling

Mer information

Senast uppdaterat

2023-01-31