With the wide application of Deep Neural Network (DNN) in the field of communication, this technique has also been applied in the coding and decoding technology, but there are few neural network structures with good performance in the decoder. This paper proposes a new polar code decoding network structure, which uses a modular network structure to train the empirical parameters in the iterative belief propagation (BP) algorithm model. The experiment part uses the new structure to implement scaling min-sum (SMS) algorithm and offset min-sum (OMS) algorithm. Through comparing the performance of the above algorithms with the traditional structure, it is found that the new structure has the advantages of better bit error rate (BER) and faster convergence performance compared with the traditional network structure.
With the wide application of Deep Neural Network (DNN) in the field of communication, this technique has also been applied in the coding and decoding technology, but there are few neural network structures with good performance in the decoder. This paper proposes a new polar code decoding network structure, which uses a modular network structure to train the empirical parameters in the iterative belief propagation (BP) algorithm model. The experiment part uses the new structure to implement scaling min-sum (SMS) algorithm and offset min-sum (OMS) algorithm. Through comparing the performance of the above algorithms with the traditional structure, it is found that the new structure has the advantages of better bit error rate (BER) and faster convergence performance compared with the traditional network structure.
In recent years, the emerging Deep Learning (DL) technology has made progress in the field of decoding. Current polar code neural network decoder has faster convergence speed and better Bit Error Rate (BER) performance than Belief Propagation (BP) decoding. However, it still has the problem of high computational complexity. Therefore, in order to improve this problem, this paper adopts the idea of improving information update in the iterative process, and proposes a Recurrent Neural Network (RNN) Offset Min-Sum (OMS) BP decoding algorithm that improves Left information update (RNN-OMSBP-L) . The simulation results show that, compared with the Deep Neural Network (DNN) BP(DNN-BP) decoding algorithm, this algorithm replaces all multiplications with a cost of 6.25% addition. Compared with the current optimized RNN OMS and approximate BP(RNN-OMS-BP) decoding algorithm, the decoding algorithm in this paper uses improved information to reduce 25% of the addition operations with almost no loss in BER performance, while saving part of the storage space overhead. Under the same BER performance, it reduces the number of iterations by 37.5%.
Deep learning recently shows strong competitiveness to improve polar code decoding. However, suffering from prohibitive training and computation complexity, the conventional deep neural network (DNN) is only possible for very short code length. In this paper, the main problems of deep learning in decoding are well solved. We first present the multiple scaled belief propagation (BP) algorithm, aiming at obtaining faster convergence and better performance. Based on this, deep neural network decoder (NND) with low complexity and latency, is proposed for any code length. The training only requires a small set of zero codewords. Besides, its computation complexity is close to the original BP. Experiment results show that the proposed (64,32) NND with 5 iterations achieves even lower bit error rate (BER) than the 30-iteration conventional BP and (512, 256) NND also outperforms conventional BP decoder with same iterations. The hardware architecture of basic computation block is given and folding technique is also considered, saving about 50% hardware cost.
In this paper, we propose two novel min-sum (MS) decoding algorithms based on deep learning for polar codes, an offset min-sum (OMS) and a scaling offset min-sum (SOMS) algorithm. The parameters of both algorithms are different from iteration to iteration, and are obtained by training over a deep neural network. Our simulation results show that the OMS algorithm has roughly the same error performance as a previously proposed multiple scaling min-sum (MSMS) algorithm, and that the SOMS algorithm performs better than all existing BP-based algorithms. Since the OMS algorithm requires only an addition as opposed to a multiplication in the MSMS algorithm, the OMS algorithm is more suitable for hardware implementation. The two proposed decoding algorithms provide a tradeoff between complexity and error performance.
In recent years, polar codes under deep learning have become a research hotspot because of their outstanding decoding performance. The neural network-based polar codes confidence propagation decoding algorithm can improve the decoding performance significantly, but the computational complexity and delay of the neural network-based polar codes confidence propagation decoding algorithm still need to be improved. In this paper, the theory of polar codes coding and the traditional polar codes confidence propagation decoding algorithm are introduced. The polar codes confidence propagation decoding algorithm based on deep neural network and recurrent neural network and the advantages and disadvantages of different decoding algorithms are mainly discussed, and the computational complexity of these algorithms is analyzed. According to the offset minimum sum approximation and scaling offset minimum sum approximation, the polar codes confidence propagation decoding algorithm based on recurrent neural network is optimized. Simulation results show that, compared with the traditional polar codes confidence propagation decoding algorithm, the decoding algorithm improves the decoding performance, reduces the computational complexity and reduces the iteration times of the algorithm. Compared with the polar codes confidence propagation decoding algorithm based on deep neural network and recurrent neural network, the multiplication and memory overhead of the algorithm are greatly reduced while the decoding performance of the algorithm is guaranteed.
With the development of communication technology, it is urgent to design channel decoding algorithms to maximize the high throughput and minimize the latency. As the capacity achieving polar codes are adopted by 5-th generation wireless system (5G), it is required to design efficient the decoding algorithms for polar codes with high performance and low complexity. Deep neural network (DNN)-based algorithms which have shown superiority in other fields, can obtain better performance using multi-scale belief propagation (BP) algorithm, whereas the decoding complexity needs to be decreased. We propose a residual neural network based belief propagation (ResNet- BP) algorithm to solve the inherent drawbacks in the existing methods, by reducing the number of variables in the network and reducing the complexity in terms of multiplication. Simulation results demonstrate that the proposed method can achieve the approximating performance of recurrent neural network-based belief propagation (RNN-BP) with a lower number of iterations.
Polar code is selected for the 5-th generation of wireless communication standard. Meanwhile, with the demand of low latency in 5G and great success in deep learning area, neural network decoder (NND) becomes a promising candidate for future decoder. However, NND is currently only feasible for very short code lengths. In this paper, we proposed a belief propagation-neural network (BP-NN) algorithm for polar codes based on partitioning. The core of our algorithm is replacing subblock of belief propagation (BP) decoder with NNDs, and using BP decoding framework to connect them. In addition, we also introduce a weight function to complete the message propagation process. Simulation results show the proposed algorithm reduces the decoding delay compared to the traditional BP algorithm and have a well bit error rate (BER) performance. At the same time, it also suitable for long polar codes.