Neural Successive Cancellation Decoding of Polar Codes

Doan, Nghia; Hashemi, Seyyed Ali; Gross, Warren J.

doi:10.1109/spawc.2018.8445986

Cited by 44 publications

(35 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since NNDs can show near MAP performance at extremely low latency for short codes, they have been studied as a new solution to low latency applications for polar codes [ 5 , 6 , 7 , 8 , 9 , 10 , 11 ]. In [ 5 , 6 ], it was shown that various neural networks are able to learn polar decoding algorithms for short codes and when fully learned, they perform closely to MAP decoding.…”

Section: DL Based Decoders For Polar Codesmentioning

confidence: 99%

“…That is, polar codes have been shown to be practically available. Recently, decoders using deep learning (DL) have been proposed to replace traditional decoders of polar codes [ 5 , 6 , 7 , 8 , 9 , 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies [ 5 , 6 , 7 , 8 , 9 , 10 , 11 , 17 ] considered learning an NND for a specific code of fixed length and rate. However, wireless standards normally use a class of codes of multiple parameter sets, since a receiver is required to have either multiple decoders each of which is specialized to a code or a decoder which is flexible to decode many codes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Training Neural Network Decoders of Rate Compatible Polar Codes via Transfer Learning

Lee

Seo

et al. 2020

Entropy

View full text Add to dashboard Cite

Neural network decoders (NNDs) for rate-compatible polar codes are studied in this paper. We consider a family of rate-compatible polar codes which are constructed from a single polar coding sequence as defined by 5G new radios. We propose a transfer learning technique for training multiple NNDs of the rate-compatible polar codes utilizing their inclusion property. The trained NND for a low rate code is taken as the initial state of NND training for the next smallest rate code. The proposed method provides quicker training as compared to separate learning of the NNDs according to numerical results. We additionally show that an underfitting problem of NND training due to low model complexity can be solved by transfer learning techniques.

show abstract

Section: DL Based Decoders For Polar Codesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Training Neural Network Decoders of Rate Compatible Polar Codes via Transfer Learning

Lee

Seo

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…We trained neural normalized min-sum (NNMS) decoders [13] for four short block codes: a (63, 45) BCH code, a (16,8) LDPC code, a (128,64) polar code, and a (200,100) LDPC code. For all experiments described in this paper, we used the Adam update rule [26] with a learning rate of 0.01, and trained on 10,000 minibatches of 120 codewords each, with added noise drawn uniformly from all signal-to-noise ratios (SNRs).…”

Section: Supervised Learning Experimentsmentioning

confidence: 99%

Learning from the Syndrome

Lugosch

Gross

2018

2018 52nd Asilomar Conference on Signals, Systems, and Computers

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce the syndrome loss, an alternative loss function for neural error-correcting decoders based on a relaxation of the syndrome. The syndrome loss penalizes the decoder for producing outputs that do not correspond to valid codewords. We show that training with the syndrome loss yields decoders with consistently lower frame error rate for a number of short block codes, at little additional cost during training and no additional cost during inference. The proposed method does not depend on knowledge of the transmitted codeword, making it a promising tool for online adaptation to changing channel conditions.

show abstract

“…However, both of them will cause high decoding latency since the serial processing mechanism of SC and the iterative processing scheme of BP. The deep learning-based decoding has been investigated to reduce the latency of polar decoding since the one-shot decoding of the neural network (NN) decoder [8][9][10]. In very short code length of polar codes, the feedforward neural network can be directly used for polar decoding, where the log-likelihood ratios (LLRs) as the input and the estimated bits as the output of the NN [8].…”

Section: Introductionmentioning

confidence: 99%

Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel

Fang

Xiao

et al. 2020

IEEE Photonics J.

View full text Add to dashboard Cite

The neural successive cancellation (NSC) decoder with tanh-based modified log-likelihood ratio (LLR) is proposed for reducing the decoding latency of polar codes over free space optical (FSO) turbulence channel. The conventional successive cancellation (SC) decoder is partitioned into multiple sub-blocks, which are replaced by multiple sub neural network (NN) decoders with tanh-based modified LLR. The recursive characteristic of the polar sequences reliability ranking given in 5G standard enables the sub-NN decoder to be uniquely determined by code length and the number of information bits. Confirmed by the simulation, the bit error rate (BER) performance of NSC decoder with tanh-based modified LLR is close to the conventional SC decoder over turbulence channel for the practical-length polar codes. Regarding turbulence-stability, the NSC decoder trained in moderate and strong turbulence conditions have stable performance in a wide range of turbulence conditions. Moreover, in comparison of decoding latency, the NSC decoder with tanh-based modified LLR takes less than 25% time steps of SC decoder in the same code length.

show abstract

Neural Successive Cancellation Decoding of Polar Codes

Cited by 44 publications

References 17 publications

On Training Neural Network Decoders of Rate Compatible Polar Codes via Transfer Learning

On Training Neural Network Decoders of Rate Compatible Polar Codes via Transfer Learning

Learning from the Syndrome

Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel

Contact Info

Product

Resources

About