An Introduction to Deep Learning for the Physical Layer

2017/02/02 by Timothy J. O’Shea, Jakob Hoydis, O'Shea, Timothy J. +1 · 27 citations
Computer Science · #Blind Source Separation Techniques #FOS: Computer and information sciences #Face and Expression Recognition #Information Theory (cs.IT) #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI) #Wireless Signal Modulation Classification

paper · pdf · doi:10.48550/arxiv.1702.00832

openalex publication_date 2017/02/02 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

We present and discuss several novel applications of deep learning for the physical layer. By interpreting a communications system as an autoencoder, we develop a fundamental new way to think about communications system design as an end-to-end reconstruction task that seeks to jointly optimize transmitter and receiver components in a single process. We show how this idea can be extended to networks of multiple transmitters and receivers and present the concept of radio transformer networks as a means to incorporate expert domain knowledge in the machine learning model. Lastly, we demonstrate the application of convolutional neural networks on raw IQ samples for modulation classification which achieves competitive accuracy with respect to traditional schemes relying on expert features. The paper is concluded with a discussion of open challenges and areas for future investigation.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Gradient-based Hyperparameter Optimization through Reversible Learning
• A Fast Learning Algorithm for Deep Belief Nets
• Multilayer feedforward networks are universal approximators
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Neural Programmer-Interpreters
• Reinforcement Learning Neural Turing Machines - Revised
• Learning to Protect Communications with Adversarial Neural Cryptography
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Convolutional Radio Modulation Recognition Networks

Cited by

• A Speculative GLRT-Backed ApproachRobust Deep Learning-Based Array Processing
• Learning Binary Autoencoder-Based Codes with Progressive Training
• Online Learning of Modular Bayesian Deep Receivers: Single-Step Adaptation with Streaming Data
• Adapt under Attack and Domain Shift: Unified Adversarial Meta-Learning and Domain Adaptation for Robust Automatic Modulation Classification
• Before AI Takes Over: Rethinking Nonlinear Signal Processing in Communications
• Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations
• SIM-Assisted End-to-End Co-Frequency Co-Time Full-Duplex System
• Adaptive End-to-End Transceiver Design for NextG Pilot-Free and CP-Free Wireless Systems
• Large-Model AI for Near Field Beam Prediction: A CNN-GPT2 Framework for 6G XL-MIMO
• CoNet-Rx: Collaborative Neural Networks for OFDM Receivers
• Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications
• Distributed learning for automatic modulation recognition in bandwidth-limited networks
• A Unified Transformer Architecture for Low-Latency and Scalable Wireless Signal Processing
• RADE for Land Mobile Radio: A Neural Codec for Transmission of Speech over Baseband FM Radio Channels
• MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts Framework
• Stacked Intelligent Metasurface for End-to-End OFDM System
• An Adaptive Environment-Aware Transformer Autoencoder for UAV-FSO with Dynamic Complexity Control
• Privacy Preserving Semantic Communications Using Vision Language Models: A Segmentation and Generation Approach
• Constellation Shaping for OFDM-ISAC Systems: From Theoretical Bounds to Practical Implementation
• Non-Identical Diffusion Models in MIMO-OFDM Channel Generation
• Experimental End-to-End Optimization of Directly Modulated Laser-based IM/DD Transmission
• Failure Tolerant Phase-Only Indoor Positioning via Deep Learning
• RFSS: A Comprehensive Multi-Standard RF Signal Source Separation Dataset with Advanced Channel Modeling
• Learning Zero Constellations for Binary MOCZ in Fading Channels
• Industrial Viewpoints on RAN Technologies for 6G
• Adaptive Source-Channel Coding for Semantic Communications
• Structured Superposition of Autoencoders for UEP Codes at Intermediate Blocklengths

Related

• Deep Learning for Wireless Physical Layer: Opportunities and Challenges
• Deep Architectures for Modulation Recognition
• Digital Signal Processing Using Deep Neural Networks
• Deep Neural Network Architectures for Modulation Classification
• Deep Modulation Embedding