Training Method of Deep Learning-Based Decoder for Punctured Polar Codes 


Vol. 43,  No. 7, pp. 1176-1181, Jul.  2018
10.7840/kics.2018.43.7.1176


PDF
  Abstract

Recently, various decoders with deep learning structures for linear codes have been proposed, and a decoder with feedforward neural network structure for polar codes has been shown to be near-optimal performance when sufficiently learned. However, in the previous research, performance was evaluated by only mother code without considering puncturing scheme for length-compatibility of polar codes. Therefore, in this paper, we show the performance of existing neural network decoder for punctured polar codes and propose a training method to efficiently learn punctured polar codes.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

E. Y. Seo, Y. J. Choi, J. Kim, S. Kim, "Training Method of Deep Learning-Based Decoder for Punctured Polar Codes," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 7, pp. 1176-1181, 2018. DOI: 10.7840/kics.2018.43.7.1176.

[ACM Style]

Eun Young Seo, Yeon Joon Choi, Jong-Hwan Kim, and Sang-Hyo Kim. 2018. Training Method of Deep Learning-Based Decoder for Punctured Polar Codes. The Journal of Korean Institute of Communications and Information Sciences, 43, 7, (2018), 1176-1181. DOI: 10.7840/kics.2018.43.7.1176.

[KICS Style]

Eun Young Seo, Yeon Joon Choi, Jong-Hwan Kim, Sang-Hyo Kim, "Training Method of Deep Learning-Based Decoder for Punctured Polar Codes," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 7, pp. 1176-1181, 7. 2018. (https://doi.org/10.7840/kics.2018.43.7.1176)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880