Novel LDPC Decoder via MLP Neural Networks

TL;DR

This paper introduces a neural network-based LDPC decoder that operates with lower complexity than traditional algorithms, offering a parallel processing approach that approximates the performance of the Sum Product Algorithm.

Contribution

It presents a novel neural network decoder for LDPC codes that reduces computational complexity while maintaining near-optimal error performance.

Findings

Neural decoder performance is close to Sum Product Algorithm.

The proposed method has lower computational complexity.

Decoding is done without probabilistic quantities.

Abstract

In this paper, a new method for decoding Low Density Parity Check (LDPC) codes, based on Multi-Layer Perceptron (MLP) neural networks is proposed. Due to the fact that in neural networks all procedures are processed in parallel, this method can be considered as a viable alternative to Message Passing Algorithm (MPA), with high computational complexity. Our proposed algorithm runs with soft criterion and concurrently does not use probabilistic quantities to decide what the estimated codeword is. Although the neural decoder performance is close to the error performance of Sum Product Algorithm (SPA), it is comparatively less complex. Therefore, the proposed decoder emerges as a new infrastructure for decoding LDPC codes.