Performance Evaluation of PAC Decoding with Deep Neural Networks

TL;DR

This paper evaluates different deep neural network architectures for decoding polarization-adjusted convolutional (PAC) codes, demonstrating that MLP decoders outperform CNN and RNN in error correction.

Contribution

It introduces and compares three types of DNN decoders for PAC codes, highlighting the superior performance of MLP decoders in error correction.

Findings

MLP decoder achieves the best error-correction performance.

DNN decoders leverage parallel computing for efficient decoding.

Extensive simulations validate the effectiveness of proposed DNN decoders.

Abstract

By concatenating a polar transform with a convolutional transform, polarization-adjusted convolutional (PAC) codes can reach the dispersion approximation bound in certain rate cases. However, the sequential decoding nature of traditional PAC decoding algorithms results in high decoding latency. Due to the parallel computing capability, deep neural network (DNN) decoders have emerged as a promising solution. In this paper, we propose three types of DNN decoders for PAC codes: multi-layer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The performance of these DNN decoders is evaluated through extensive simulation. Numerical results show that the MLP decoder has the best error-correction performance under a similar model parameter number.