In this paper, we proposed a block neural network (BlockNN) algorithm for polar code. We equally divide the 2nbit polar code into many small sub-blocks according to the encoding rules of polar code, then put these sub-blocks into the neural network of the same structure for processing. This decoding algorithm is non-iterative and inherently enables a high level of parallelization, while showing a competitive BER(bit error arte) performance. On the aspect of hardware implementation, this decoding structure of the neural network can be multiplexed and the computational complexity does not increase with the code length, only related to the size of the block.
In this paper, we proposed a block neural network (BlockNN) algorithm for polar code. We equally divide the 2nbit polar code into many small sub-blocks according to the encoding rules of polar code, then put these sub-blocks into the neural network of the same structure for processing. This decoding algorithm is non-iterative and inherently enables a high level of parallelization, while showing a competitive BER(bit error arte) performance. On the aspect of hardware implementation, this decoding structure of the neural network can be multiplexed and the computational complexity does not increase with the code length, only related to the size of the block.
The training complexity of deep learning-based channel decoders scales exponentially with the codebook size and therefore with the number of information bits. Thus, neural network decoding (NND) is currently only feasible for very short block lengths. In this work, we show that the conventional iterative decoding algorithm for polar codes can be enhanced when sub-blocks of the decoder are replaced by neural network (NN) based components. Thus, we partition the encoding graph into smaller sub-blocks and train them individually, closely approaching maximum a posteriori (MAP) performance per sub-block. These blocks are then connected via the remaining conventional belief propagation decoding stage(s). The resulting decoding algorithm is non-iterative and inherently enables a highlevel of parallelization, while showing a competitive bit error rate (BER) performance. We examine the degradation through partitioning and compare the resulting decoder to state-of-the art polar decoders such as successive cancellation list and belief propagation decoding.
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.
Polar codes using successive-cancellation decoding always suffer from high latency for its serial nature. Fast simplified successive-cancellation decoding algorithm improves the situation in theoretically but not performs well as expected in practical for the workload of nodes identification and the existence of many short blocks. Meanwhile, Neural network (NN) based decoders have appeared as potential candidates to replace conventional decoders for polar codes. But the exponentially increasing training complexity with information bits is unacceptable which means it is only suitable for short codes. In this paper, we present an improvement that increases decoding efficiency without degrading the error-correction performance. The long polar codes are divided into several sub-blocks, some of which can be decoded adopting fast maximum likelihood decoding method and the remained parts are replaced by several short codes NN decoders. The result shows that time steps the proposed algorithm need only equal to 79.8% of fast simplified successive-cancellation decoders require. Moreover, it has up to 21.2 times faster than successive-cancellation decoding algorithm. More importantly, the proposed algorithm decreases the hardness when applying in some degree.
In order to overcome the problems of high bit error rate, delay and complexity, research on CNN polar decoding algorithm is proposed. This method uses CNN as the decoder, analyzes the difference between the traditional algorithm and the CNN decoder, adjusts the network parameters, obtains the best parameters, makes the decoder optimal, and in the channel coding scheme, the encoding and decoding complexity of polarized codes is low, and it has been strictly proved that they can reach the Shannon limit. However, there are a lot of shortcomings in the existing traditional decoding algorithms, With the maturity of deep learning, the application of deep learning to the field of communication, deep learning has advantage of powerful computing, and neural network after training is static, once only need data through the network, so the deep learning was applied to the polarization code decoding process, can effectively reduce the decoding delay and improve the efficiency of decoding, this paper mainly studies convolution decoder of neural networks in all aspects of performance, can get the conclusion by experiment, with the increase of the number of iterations network decoding ability improved, error performance is getting better and better, and CNN has obvious advantages.
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%.
Error-correction in the communication module of IoT systems is a mission-critical task. The Polar code is one of the modern 5G wireless technologies. Most conventional decoding methods are iterative. It is interesting to investigate the feasibility of AI methodology, such as machine learning, for small Polar codes. In this paper, we design a small artificial neural network for this purpose. It is shown that this neural network can successfully decode four small Polar codes: both non-systematic and systematic, with codeword length 8 and 16, respectively.