A Low-Complexity Neural Normalized Min-Sum LDPC Decoding Algorithm using Tensor-Train Decomposition

Compared with traditional low-density parity-check (LDPC) decoding algorithms, the current model-driven deep learning (DL)-based LDPC decoding algorithms face the disadvantage of high computational complexity. Based on the Neural Normalized Min-Sum (NNMS) algorithm, we propose a low-complexity model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE communications letters Jg. 26; H. 12; S. 1
Hauptverfasser: Liang, Yuanhui, Lam, Chan-Tong, Ng, Benjamin K.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Artificial neural networks
Bit error rate
Complexity
Computational complexity
Decoding
Decomposition
Error correcting codes
Iterative decoding
Machine learning
Mathematical analysis
Model-Driven LDPC Decoding
Neural Normalized Min-Sum
Propagation losses
Symbols
Syndrome Loss
Tensor-Train Decomposition
Tensors
ISSN:1089-7798, 1558-2558
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Compared with traditional low-density parity-check (LDPC) decoding algorithms, the current model-driven deep learning (DL)-based LDPC decoding algorithms face the disadvantage of high computational complexity. Based on the Neural Normalized Min-Sum (NNMS) algorithm, we propose a low-complexity model-driven DL-based LDPC decoding algorithm using Tensor-Train (TT) decomposition and syndrome loss function, called TT-NNMS+ algorithm. Our experiments show that the proposed TT-NNMS+ algorithm is more competitive than the NNMS algorithm in terms of bit error rate (BER) performance, memory requirement and computational complexity.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2022.3207506