Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism

Abstract: 

Polar codes have drawn much attention and been adopted in 5G New Radio (NR) due to their capacity-achieving performance. Recently, as the emerging deep learning (DL) technique has breakthrough achievements in many fields, neural network decoder was proposed to obtain faster convergence and better performance than belief propagation (BP) decoding. However, neural networks are memory-intensive and hinder the deployment of DL in communication systems. In this work, a low-complexity recurrent neural network (RNN) polar decoder with codebook-based weight quantization is proposed. Our test results show that we can effectively reduce the memory overhead by 98% and alleviate computational complexity with slight performance loss.

up
0 users have voted:

Paper Details

Authors:
Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu
Submitted On:
7 May 2019 - 8:34pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Chieh-Fang Teng
Paper Code:
DISPS-L2.1
Document Year:
2019
Cite

Document Files

Presentation Slides

(27)

Subscribe

[1] Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu, "Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3974. Accessed: Sep. 17, 2019.
@article{3974-19,
url = {http://sigport.org/3974},
author = {Chieh-Fang Teng; Chen-Hsi (Derek) Wu; Andrew Kuan-Shiuan Ho; and An-Yeu (Andy) Wu },
publisher = {IEEE SigPort},
title = {Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism},
year = {2019} }
TY - EJOUR
T1 - Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism
AU - Chieh-Fang Teng; Chen-Hsi (Derek) Wu; Andrew Kuan-Shiuan Ho; and An-Yeu (Andy) Wu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3974
ER -
Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu. (2019). Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism. IEEE SigPort. http://sigport.org/3974
Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu, 2019. Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism. Available at: http://sigport.org/3974.
Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu. (2019). "Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism." Web.
1. Chieh-Fang Teng, Chen-Hsi (Derek) Wu, Andrew Kuan-Shiuan Ho, and An-Yeu (Andy) Wu. Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3974