Improved polar decoder based on deep learning

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.

[1]  Keshab K. Parhi,et al.  Early Stopping Criteria for Energy-Efficient Low-Latency Belief-Propagation Polar Code Decoders , 2014, IEEE Transactions on Signal Processing.

[2]  Stephan ten Brink,et al.  Scaling Deep Learning-Based Decoding of Polar Codes via Partitioning , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[3]  Keshab K. Parhi,et al.  Low-Latency Sequential and Overlapped Architectures for Successive Cancellation Polar Decoder , 2013, IEEE Transactions on Signal Processing.

[4]  Xiaohu You,et al.  Pipelined belief propagation polar decoders , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[5]  Xiaohu You,et al.  Efficient early termination schemes for belief-propagation decoding of polar codes , 2015, 2015 IEEE 11th International Conference on ASIC (ASICON).

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[10]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[11]  Keshab K. Parhi,et al.  VLSI digital signal processing systems , 1999 .

[12]  Erdal Arikan,et al.  Channel Polarization: A Method for Constructing Capacity-Achieving Codes for Symmetric Binary-Input Memoryless Channels , 2008, IEEE Transactions on Information Theory.

[13]  Keshab K. Parhi,et al.  Reduced-latency SC polar decoder architectures , 2012, 2012 IEEE International Conference on Communications (ICC).

[14]  Alptekin Pamuk,et al.  An FPGA implementation architecture for decoding of polar codes , 2011, 2011 8th International Symposium on Wireless Communication Systems.