Iterative Decoding Algorithms Powered by Deep Learning

In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the traditional BP algorithm. Previous investigations have shown that assigning pre-trained weights to BP messages can significantly improve the decod...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 12th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) s. 1 - 6
Hlavní autoři: Jovanovic, Dimitrije, Ivanis, Predrag
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.06.2025
Témata:
AWGN channel
AWGN channels
Belief propagation
Bit error rate
Codes
Decoding
Deep learning
Iterative decoding
MDPC codes
neural network
Neural networks
TensorFlow
Training
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the traditional BP algorithm. Previous investigations have shown that assigning pre-trained weights to BP messages can significantly improve the decoding performance in case of high-density parity-check (HDPC) codes, by reducing the negative impact of short cycles. These weights are trained by a neural network whose structure matches the trellis of the decoder. Specifically, we show that medium-density paritycheck (MDPC) codes decoded with neural BP algorithm can achieve lower bit error rate versus HDPC codes with the same codeword length and the same code rate.
DOI:10.1109/IcETRAN66854.2025.11114279