Polar Decoding on Sparse Graphs with Deep Learning

11/24/2018
by   Weihong Xu, et al.
0

In this paper, we present a sparse neural network decoder (SNND) of polar codes based on belief propagation (BP) and deep learning. At first, the conventional factor graph of polar BP decoding is converted to the bipartite Tanner graph similar to low-density parity-check (LDPC) codes. Then the Tanner graph is unfolded and translated into the graphical representation of deep neural network (DNN). The complex sum-product algorithm (SPA) is modified to min-sum (MS) approximation with low complexity. We dramatically reduce the number of weight by using single weight to parameterize the networks. Optimized by the training techniques of deep learning, proposed SNND achieves comparative decoding performance of SPA and obtains about 0.5 dB gain over MS decoding on (128,64) and (256,128) codes. Moreover, 60 % complexity reduction is achieved and the decoding latency is significantly lower than the conventional polar BP.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/22/2017

Sparse Graphs for Belief Propagation Decoding of Polar Codes

We describe a novel approach to interpret a polar code as a low-density ...
research
02/07/2021

Learning to Decode Protograph LDPC Codes

The recent development of deep learning methods provides a new approach ...
research
10/29/2018

Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism

Polar codes have drawn much attention and been adopted in 5G New Radio (...
research
07/22/2019

Deep Learning Assisted Sum-Product Detection Algorithm for Faster-than-Nyquist Signaling

A deep learning assisted sum-product detection algorithm (DL-SPA) for fa...
research
02/01/2022

Automorphism Ensemble Decoding of Quasi-Cyclic LDPC Codes by Breaking Graph Symmetries

We consider automorphism ensemble decoding (AED) of quasi-cyclic (QC) lo...
research
12/15/2020

A Novel Sum-Product Detection Algorithm for Faster-than-Nyquist Signaling: A Deep Learning Approach

A deep learning assisted sum-product detection algorithm (DL-SPDA) for f...
research
07/29/2022

Graph Neural Networks for Channel Decoding

In this work, we propose a fully differentiable graph neural network (GN...

Please sign up or login with your details

Forgot password? Click here to reset