A Generalized Data Representation and Training-Performance Analysis for Deep Learning-Based Communications Systems

TL;DR

This paper introduces a generalized data representation for deep learning-based communication autoencoders, improving data rate and channel capacity while reducing training complexity, and analyzes the impact of SNR on training performance.

Contribution

It proposes a novel GDR scheme for DL communication systems, enhancing data rate and capacity with lower complexity, and studies the effect of SNR on training outcomes.

Findings

GDR achieves higher channel capacity than traditional schemes.

Training at high SNR improves autoencoder performance.

GDR reduces training complexity while maintaining BER performance.

Abstract

Deep learning (DL)-based autoencoder is a potential architecture to implement end-to-end communication systems. In this letter, we first give a brief introduction to the autoencoder-represented communication system. Then, we propose a novel generalized data representation (GDR) aiming to improve the data rate of DL-based communication systems. Finally, simulation results show that the proposed GDR scheme has lower training complexity, comparable block error rate performance and higher channel capacity than the conventional one-hot vector scheme. Furthermore, we investigate the effect of signal-to-noise ratio (SNR) in DL-based communication systems and prove that training at a high SNR could produce a good training performance for autoencoder.