Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEICE Communications Express

Enhancing Neural Network Decoder Performance for Convolutional Polar Codes

Yuto Nakamura, Nobuhiko Miki, Satoshi SUYAMA, Satoshi Nagata

Published Jun 2, 2026• 0 citations
Publisher
DOI
10.23919/comex.2026xbl0058

Related papers

Performance analysis of neural network-based polar decoding algorithms with different code rates

Shridhar B. Devamane, Rajeshwari L. Itagi

Iran Journal of Computer Science•Nov 15, 2021•3 citations

Investigation on Information Set Optimization of Neural Network Decoders Suitable for Polar and Convolutional Polar Codes

Yuto Nakamura, Satoshi Suyama, Satoshi Nagata +1 more

One of the possible methods for obtaining reduced latency is the use of neural network decoder (NND) on polar codes. We also apply the convolutional polar codes. We propose an iterative approach to optimize the information set for NND. The proposed approach reduces the block error rate (BLER) performance by exchanging one bit in the information set for one bit in the frozen set. This process is performed until the improvement is saturated. The simulation results show that the BLER performance was enhanced by using the proposed iterative approach for polar codes and convolutional polar codes.

International Conference on Information Networking•Jan 17, 2024•2 citations

Survey on Decoding Schemes of the Polar Code Using the Deep Learning

Jida Yang, Yuan Liu

Lecture notes in electrical engineering•Jan 1, 2023•2 citations

Polarization Decoding Algorithm Based on Convolutional Neural Network

Yang Xiao-jing, Ning Wang

In order to solve the problem that the existing Polar code decoding algorithm based on neural network can only decode short codewords (codewords length N≤64), a new decoding algorithm using convolution neural network for long codewords (N≥512) was put forward. Instead of using a fixed drawn from the data sample proportion as training set and test set, the neural network parameters epoch and batch were used to control the neural network input, and the data explosion problem caused by the long codewords was solved. In addition, the influence of batch and epoch parameters on the decoding performance of convolution neural network was explored and the performance difference of neural network using different activation functions were investigated. Simulation results show that with the traditional SCL (successive cancellation list, L=2) decoding algorithm, convolution neural network in low signal-to-noise ratio on the performance is better than that of SCL (L=2), in high signal-to-noise ratio and SCL (L=2) algorithm of similar performance, and the larger the training data set, the better the decoding performance of neural network.

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)•Dec 11, 2020•0 citations

A Decoding Algorithm for Polar Codes Based on PD-CNN

Xu Peng, Lingjun Kong, Shengmei Zhao +1 more

Xinhao Chuli•Jan 1, 2019•1 citation

BP Flip Decoding Algorithm of Polar Code Based on Convolutional Neural Network

Xiaojun Zhang, Yue Qiu, Wenxiu Kong +2 more

Polar code has been selected as the control channel coding scheme for the 5th generation mobile communication technology (5G), and the performance of short polar codes is receiving intensive attention. However, belief propagation (BP) algorithm suffers from performance loss under short codes. In order to improve decoding performance, this paper proposes a BP flip decoding algorithm based on convolutional neural network (CNN-BP flip). Cyclic redundancy check (CRC) is used to check the results after BP decoding, and extracts the left messages in the factor graph of the last iteration that have not passed the CRC. The extracted messages are mapped into an image as the input of the convolutional neural network (CNN), the network model is adopted to classify the flipping bits. Compared with the critical set-based BP flip (CS-BP flip) algorithm, the CNN-BP flip algorithm achieves 0.23 dB gain at the number of flip attempts T1=5 and the block error rate (BLER)=10-2for polar code with N=64.

IEEE/CIC International Conference on Communications in China (ICCC)•Aug 11, 2022•3 citations
One of the possible methods for obtaining reduced latency is the use of neural network decoder (NND) on polar codes. We also apply the convolutional polar codes. We propose an iterative approach to optimize the information set for NND. The proposed approach reduces the block error rate (BLER) performance by exchanging one bit in the information set for one bit in the frozen set. This process is performed until the improvement is saturated. The simulation results show that the BLER performance was enhanced by using the proposed iterative approach for polar codes and convolutional polar codes.
In order to solve the problem that the existing Polar code decoding algorithm based on neural network can only decode short codewords (codewords length N≤64), a new decoding algorithm using convolution neural network for long codewords (N≥512) was put forward. Instead of using a fixed drawn from the data sample proportion as training set and test set, the neural network parameters epoch and batch were used to control the neural network input, and the data explosion problem caused by the long codewords was solved. In addition, the influence of batch and epoch parameters on the decoding performance of convolution neural network was explored and the performance difference of neural network using different activation functions were investigated. Simulation results show that with the traditional SCL (successive cancellation list, L=2) decoding algorithm, convolution neural network in low signal-to-noise ratio on the performance is better than that of SCL (L=2), in high signal-to-noise ratio and SCL (L=2) algorithm of similar performance, and the larger the training data set, the better the decoding performance of neural network.
Polar code has been selected as the control channel coding scheme for the 5th generation mobile communication technology (5G), and the performance of short polar codes is receiving intensive attention. However, belief propagation (BP) algorithm suffers from performance loss under short codes. In order to improve decoding performance, this paper proposes a BP flip decoding algorithm based on convolutional neural network (CNN-BP flip). Cyclic redundancy check (CRC) is used to check the results after BP decoding, and extracts the left messages in the factor graph of the last iteration that have not passed the CRC. The extracted messages are mapped into an image as the input of the convolutional neural network (CNN), the network model is adopted to classify the flipping bits. Compared with the critical set-based BP flip (CS-BP flip) algorithm, the CNN-BP flip algorithm achieves 0.23 dB gain at the number of flip attempts T1=5 and the block error rate (BLER)=10-2for polar code with N=64.