Polarization code decoding algorithm based on deep learning

Abstract

The invention discloses a polarization code decoding algorithm based on deep learning. A multi-dimension zooming Min-sum belief propagation decoding algorithm is provided to accelerate the convergence speed of the decoding algorithm; and then, a polarization code decoder based on a deep neural network is realized according to the similarity between the factor graph of the BP algorithm and the deep neural network, a deep neural network decoder is trained by using the deep learning technology, compared with the original BP decoding algorithm, the decoding iterations of 90% is reduced, and meanwhile better decoding performance is obtained; and finally the invention provides hardware implementation of a fundamental operation module of the deep neural network polarization code decoder, and 50% of hardware consumption is reduced by using the hardware folding technology.

Description

technical field [0001] The invention belongs to the field of deep neural network and polar code decoding, and in particular relates to a polar code decoding algorithm based on deep learning. Background technique [0002] Polar code (Polar code) is a coding method that can tend to the Shannon limit proposed by Erdal Arikan in a 2009 paper "Channelpolarization: A method for constructing capacity-achieving codes for symmetric binary-input memoryless channels". The channel polarization phenomenon means that when the number of channels tends to infinity, some channels tend to be perfect, while some channels tend to be pure noise channels. Based on this channel polarization phenomenon, a better channel among the combined channels is selected to construct a polar code. Polar code is one of the very important technologies in the fifth generation (5G) mobile communication system. [0003] The two most common decoding algorithms for polar codes are the successive elimination (SC) al...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: In view of the above problems, the present invention proposes a polar code decoding algorithm based on deep learning, which overcomes the problem of slow convergence speed of the existing polar code BP decoding algorithm under low signal-to-noise ratio, and uses deep learning technology to achieve Achieve better decoding performance with fewer iterations, reducing decoding complexity and decoding delay

Images