Deep Learning in Physical Layer Communications

By Zhijin Qin, Hao Ye, Geoffrey Y. Li, Biing-Hwang Fred Juang. IEEE wireless communications, 2018

641 citations recorded by the source corpus.

DL has shown great potential to revolutionize communication systems. This article provides an overview of the recent advancements in DL-based physical layer communications. DL can improve the performance of each individual block in communication systems or optimize the whole transmitter/receiver. Therefore, we categorize the applications of DL in physical layer communications into systems with and without block structures. For DL-based communication systems with the block structure, we demonstrate the power of DL in signal compression and signal detection. We also discuss the recent endeavors in developing DL-based end-to-end communication systems. Finally, potential research directions are identified to boost intelligent physical layer communications. Introduction

Subfields: Aerospace Engineering, Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e7f6fd860c157b4b1908e68b778c782ba721e889

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Signal Processing

Citations in the corpus

6G and Beyond: The Future of Wireless Communications Systems (2020, background): “Such tasks often do not yield low complexity optimal solutions in complex channels [75], and thus parallel processing inherent in machine learning can be favorably leveraged to enhance computational capacity.”
Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, methodology): “Surveys on the use of ANNs to implement encoding/decoding operations as well as channel estimation tasks with limited side information have appeared in [184], [185].”
A Very Brief Introduction to Machine Learning With Applications to Communication Systems (2018, background): “Unlike other review papers such as [9]–[11], the presentation aims at highlighting conditions under which the use of machine learning is justified in”
Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems (2019, background): “(ML) is more powerful to uncover the inherent characteristics inside data/signals collected in an end-to-end manner and thus can achieve better performance when addressing various problems in wireless communications [14].”
A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, background): “Recently, supervised deep learning algorithms were also adopted in wireless networks [205].”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “Moreover, a survey on the recent advancements of employing DL at the physical layer of wireless communication systems is conducted in [93], where the application of DL at the physical layer is categorized into blocked or without blocked structured.”
A Full Dive Into Realizing the Edge-Enabled Metaverse: Visions, Enabling Technologies, and Challenges (2022, background): “the information required for the respective task/goal [139].”
Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges (2022, positive): “Following the success of DL in the individual block optimization in the physical layer [46], [47], [48], [49], [50], DL-based end-to-end communication systems have emerged as another potential direction to outperform the conventional communication structure in block error rate (BLER) and BER perform”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, methodology): “On the contrary, the learning based data-driven methods provide a new way for handling the imperfection of the assumed channel models [1].”
Semantic Communications: Principles and Challenges (2021, background): “Recent advancements on deep learning (DL) and its applications, such as natural language processing (NLP), speech recognition, and computer vision provide significant insights on developing semantic communications [3], [7].”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, positive): “Finally, [40, 41] provided an overview on the recent advances in DL-based physical layer communications and [42] suggested the potential applications of DL to the physical layer.”
Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis (2019, background): “DL recently made tremendous strides in several aspects, including computer vision, natural language processing, and wireless communications [15]–[17].”
Model-Driven Deep Learning for MIMO Detection (2020, background): “Recently, it has been applied in physical layer communications [11]–[13], such as channel estimation [14]–[16], CSI feedback [17], signal detection [18]–[26], channel coding [27], [28], and end-to-end transceiver design [29], [30].”
A Lite Distributed Semantic Communication System for Internet of Things (2020, methodology): “With the recent advancements on DL, it is promising to represent a traditional transceiver or each individual signal processing block by a deep neural network (DNN) [13].”
Deep Learning Enabled Semantic Communication Systems (2020, methodology): “The main contributions of this paper are summarized as follows: Based on the Transformer [16], a novel framework for the DeepSC is proposed, which can effectively extract the semantic information from texts with robustness to noise.”
Semantic Communication Systems for Speech Transmission (2021, background): “INTELLIGENT communications have attracted intensive attention for traditional communication systems [1].”