Opening the Black Box of Deep Neural Networks in Physical Layer Communication

TL;DR

This paper investigates the inner workings of deep neural networks in physical layer communication, analyzing their performance, computational cost, and information flow using information theory.

Contribution

It provides a quantitative analysis of DNN performance in physical layer communication and explores their information flow, bridging the gap between empirical results and theoretical understanding.

Findings

DNNs achieve comparable performance to traditional methods.

Analysis of computational complexity of DNN-based systems.

Experimental validation of information flow in DNN communication models.

Abstract

Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems. However, most studies in the physical layer have tended to focus on the application of DNN models to wireless communication problems but not to theoretically understand how does a DNN work in a communication system. In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques and their cost in terms of computational complexity. We further investigate and also experimentally validate how information is flown in a DNN-based communication system under the information theoretic concepts.