Spiking Neural Belief Propagation Decoder for Short Block Length LDPC Codes

TL;DR

This paper introduces a spiking neural network-based belief propagation decoder for LDPC codes that improves performance at high SNRs, operates without SNR knowledge, and is energy-efficient.

Contribution

It presents a novel SNN-based decoding algorithm for LDPC codes that outperforms traditional methods at high SNRs and is SNR-agnostic.

Findings

Outperforms sum-product decoder at high SNRs

Achieves similar BER to normalized sum-product decoding

Operates without SNR knowledge, showing robustness

Abstract

Spiking neural networks (SNNs) are neural networks that enable energy-efficient signal processing due to their event-based nature. This paper proposes a novel decoding algorithm for low-density parity-check (LDPC) codes that integrates SNNs into belief propagation (BP) decoding by approximating the check node update equations using SNNs. For the (273,191) and (1023,781) finite-geometry LDPC code, the proposed decoder outperforms sum-product decoder at high signal-to-noise ratios (SNRs). The decoder achieves a similar bit error rate to normalized sum-product decoding with successive relaxation. Furthermore, the novel decoding operates without requiring knowledge of the SNR, making it robust to SNR mismatch.