Deep Learning Aided SCL Decoding of Polar Codes with Shifted-Pruning

Recently,a generalized successive cancel-lation list(SCL)decoder implemented with shifted-pruning(SP)scheme,namely the SCL-SP-ω decoder,is presented for polar codes,which is able to shift the pruning window at most ω times during each SCL re-decoding attempt to prevent the correct path from being eliminated.The candidate positions for apply-ing the SP scheme are selected by a shifting met-ric based on the probability that the elimination oc-curs.However,the number of exponential/logarithm operations involved in the SCL-SP-ω decoder grows linearly with the number of information bits and list size,which leads to high computational complexity.In this paper,we present a detailed analysis of the SCL-SP-ω decoder in terms of the decoding perfor-mance and complexity,which unveils that the choice of the shifting metric is essential for improving the decoding performance and reducing the re-decoding attempts simultaneously.Then,we introduce a sim-plified metric derived from the path metric(PM)do-main,and a custom-tailored deep learning(DL)net-work is further designed to enhance the efficiency of the proposed simplified metric.The proposed metrics are both free of transcendental functions and hence,are more hardware-friendly than the existing metrics.Simulation results show that the proposed DL-aided metric provides the best error correction performance as comparison with the state of the art.