Learning to Decode Linear Codes Using Deep Learning

TL;DR

This paper introduces a deep learning-based decoding method for linear codes that enhances belief propagation by learning edge weights, maintaining codeword independence, and demonstrating improved performance on high-density parity check codes.

Contribution

The paper presents a novel deep learning approach that generalizes belief propagation by training edge weights, preserving codeword independence, and reducing training complexity.

Findings

Improved decoding performance on high-density parity check codes

Preservation of belief propagation's codeword independence property

Efficient training using a single codeword

Abstract

A novel deep learning method for improving the belief propagation algorithm is proposed. The method generalizes the standard belief propagation algorithm by assigning weights to the edges of the Tanner graph. These edges are then trained using deep learning techniques. A well-known property of the belief propagation algorithm is the independence of the performance on the transmitted codeword. A crucial property of our new method is that our decoder preserved this property. Furthermore, this property allows us to learn only a single codeword instead of exponential number of code-words. Improvements over the belief propagation algorithm are demonstrated for various high density parity check codes.