Generalized Concatenated Polar Auto-Encoder: A Deep Learning Based Polar Coding Scheme

We propose a channel auto-encoder which incorporates the encoding and decoding structure of classical generalized concatenated code (GCC) based on polar codes. The outer encoder and decoder of classical GCC polar codes are implemented by non-linear functions parameterized with a transformer based ne...

Full description

Saved in:
Bibliographic Details
Published in:IEEE Global Communications Conference (Online) pp. 1942 - 1947
Main Authors: Saber, Hamid, Bae, Jung Hyun
Format: Conference Proceeding
Language:English
Published: IEEE 08.12.2024
Subjects:
Channel Auto-encoder
Codes
Concatenated codes
Decoding
Deep learning
Encoding
Global communication
Neural networks
Polar codes
Reliability
SC Decoding
Transformers
ISSN:2576-6813
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a channel auto-encoder which incorporates the encoding and decoding structure of classical generalized concatenated code (GCC) based on polar codes. The outer encoder and decoder of classical GCC polar codes are implemented by non-linear functions parameterized with a transformer based neural network. Our results show that the proposed scheme results in enhanced reliability of classical polar codes under SC decoding.
ISSN:2576-6813
DOI:10.1109/GLOBECOM52923.2024.10901269