Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding

Authors

  • Siyu Liao Rutgers University
  • Chunhua Deng Rutgers University
  • Miao Yin Rutgers University
  • Bo Yuan Rutgers university

Keywords:

Applications, Other Applications, Probabilistic Graphical Models, (Deep) Neural Network Algorithms

Abstract

Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot achieve high decoding performance and low complexity simultaneously. To overcome this challenge, in this paper we propose doubly residual neural (DRN) decoder. By integrating both the residual input and residual learning to the design of neural channel decoder, DRN enables significant decoding performance improvement while maintaining low complexity. Extensive experiment results show that on different types of channel codes, our DRN decoder consistently outperform the state-of-the-art decoders in terms of decoding performance, model sizes and computational cost.

Downloads

Published

2021-05-18

How to Cite

Liao, S., Deng, C., Yin, M., & Yuan, B. (2021). Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8574-8582. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17040

Issue

Section

AAAI Technical Track on Machine Learning III