?
Method of Critical Set construction for Successive Cancellation List Decoder of Polar Codes Based on Deep Learning of Neural Networks
The Successive Cancellation List (SCL) algorithm is a widely used decoding technique in communication systems. However, constructing the critical set for SCL decoding is a challenging task, as it requires a large number of computations and can lead to significant decoding delays. In this paper, a new approach to critical set construction for SCL decoding is proposed, which is based on deep learning of neural networks with special structure and activation functions.The proposed method is shown to significantly reduce the cardinality of the critical set required for achieving the target frame error rate, when used with an SCL decoder with a list size of 8. Simulation results demonstrate that the proposed method outperforms existing methods in terms of reducing decoding delay, while maintaining high decoding accuracy.The key innovation of the proposed approach lies in the use of deep learning techniques to learn the structure of the critical set, which enables the construction of a more efficient and compact set. This approach has the potential to significantly improve the performance of SCL decoding in practical communication systems, where decoding delay is a critical factor.