Iterative Error Decimation for Syndrome-Based Neural Network Decoders

TL;DR

This paper presents an iterative neural network decoder that improves error correction for BCH codes by sequentially refining error pattern estimates, outperforming existing neural decoders and adaptable to various syndrome-based methods.

Contribution

Introduces a novel iterative syndrome-based neural network decoder that enhances error correction and can be integrated with existing decoders without retraining.

Findings

Outperforms existing neural decoders on BCH codes

Flexible and can be applied on top of any syndrome-based DNN decoder

Demonstrates improved decoding accuracy through simulation

Abstract

In this letter, we introduce a new syndrome-based decoder where a deep neural network (DNN) estimates the error pattern from the reliability and syndrome of the received vector. The proposed algorithm works by iteratively selecting the most confident positions to be the error bits of the error pattern, updating the vector received when a new position of the error pattern is selected. Simulation results for the (63,45) and (63,36) BCH codes show that the proposed approach outperforms existing neural network decoders. In addition, the new decoder is flexible in that it can be applied on top of any existing syndrome-based DNN decoder without retraining.