FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training

12/07/2022

∙

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.

READ FULL TEXT

FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training

Design of an FPGA-based USB 3.0 device controller

Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference

A Highly Parallel FPGA Implementation of Sparse Neural Network Training

Low Precision Constant Parameter CNN on FPGA

Efficient Hardware Implementation of Incremental Learning and Inference on Chip

Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices

ANDROMEDA: An FPGA Based RISC-V MPSoC Exploration Framework

FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training

Related Research

Design of an FPGA-based USB 3.0 device controller

Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference

A Highly Parallel FPGA Implementation of Sparse Neural Network Training

Low Precision Constant Parameter CNN on FPGA

Efficient Hardware Implementation of Incremental Learning and Inference on Chip

Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices

ANDROMEDA: An FPGA Based RISC-V MPSoC Exploration Framework