Deep Learning-Based Communication Over the Air
arXiv:1707.03384 · doi:10.1109/JSTSP.2017.2784180
Abstract
End-to-end learning of communications systems is a fascinating novel concept that has so far only been validated by simulations for block-based transmissions. It allows learning of transmitter and receiver implementations as deep neural networks (NNs) that are optimized for an arbitrary differentiable end-to-end performance metric, e.g., block error rate (BLER). In this paper, we demonstrate that over-the-air transmissions are possible: We build, train, and run a complete communications system solely composed of NNs using unsynchronized off-the-shelf software-defined radios (SDRs) and open-source deep learning (DL) software libraries. We extend the existing ideas towards continuous data transmission which eases their current restriction to short block lengths but also entails the issue of receiver synchronization. We overcome this problem by introducing a frame synchronization module based on another NN. A comparison of the BLER performance of the "learned" system with that of a practical baseline shows competitive performance close to 1 dB, even without extensive hyperparameter tuning. We identify several practical challenges of training such a system over actual channels, in particular the missing channel gradient, and propose a two-step learning procedure based on the idea of transfer learning that circumvents this issue.
References in corpus (3)
Cited by in corpus (119)
- Deep Learning Enabled Semantic Communication Systems
- Learning to Detect
- Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks
- End-to-end Deep Learning of Optical Fiber Communications
- Neural Network Detection of Data Sequences in Communication Systems
- A Deep Learning Framework for Optimization of MISO Downlink Beamforming
- An Iterative BP-CNN Architecture for Channel Decoding
- Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning
- Deep Source-Channel Coding for Sentence Semantic Transmission with HARQ
- Hybrid Precoding for Multi-User Millimeter Wave Massive MIMO Systems: A Deep Learning Approach
- SR2CNN: Zero-Shot Learning for Signal Recognition
- Deep Learning Based MIMO Communications
- Deep Learning in Mobile and Wireless Networking: A Survey
- Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
- DeepReceiver: A Deep Learning-Based Intelligent Receiver for Wireless Communications in the Physical Layer
- Scoring the Terabit/s Goal:Broadband Connectivity in 6G
- End-to-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks
- Learned Conjugate Gradient Descent Network for Massive MIMO Detection
- Deep Learning Based Sphere Decoding
- Interference Suppression Using Deep Learning: Current Approaches and Open Challenges
- A Survey on Semantic Communications for Intelligent Wireless Networks
- Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification
- AI-Aided Online Adaptive OFDM Receiver: Design and Experimental Results
- Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics
- Learning for Detection: MIMO-OFDM Symbol Detection through Downlink Pilots
- Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
- 6G Takes Shape
- End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
- Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
- Deep Learning for Wireless Physical Layer: Opportunities and Challenges
- Next-generation Wireless Solutions for the Smart Factory, Smart Vehicles, the Smart Grid and Smart Cities
- Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications
- Machine Learning for MU-MIMO Receive Processing in OFDM Systems
- Gradient-free training of autoencoders for non-differentiable communication channels
- Recent Advances in Deep Learning for Channel Coding: A Survey
- A Tutorial on Ultra-Reliable and Low-Latency Communications in 6G: Integrating Domain Knowledge into Deep Learning
- Deep Learning-Based Channel Estimation for High-Dimensional Signals
- Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration
- Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities
- The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications
- Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
- Data-driven Network Simulation for Performance Analysis of Anticipatory Vehicular Communication Systems
- Towards Optimal Power Control via Ensembling Deep Neural Networks
- Conditional Mutual Information Neural Estimator
- Deep Learning for Communication over Dispersive Nonlinear Channels: Performance and Comparison with Classical Digital Signal Processing
- Syndrome-Enabled Unsupervised Learning for Neural Network-Based Polar Decoder and Jointly Optimized Blind Equalizer
- Channel Agnostic End-to-End Learning based Communication Systems with Conditional GAN
- End-to-End Learning for Symbol-Level Precoding and Detection with Adaptive Modulation
- Fueling the Next Quantum Leap in Cellular Networks: Embracing AI in 5G Evolution towards 6G
- DeepTurbo: Deep Turbo Decoder
- Learning-Aided Physical Layer Attacks Against Multicarrier Communications in IoT
- Full-Duplex Millimeter Wave MIMO Channel Estimation: A Neural Network Approach
- Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges
- Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
- A Lite Distributed Semantic Communication System for Internet of Things
- Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels
- Deep Learning based End-to-End Wireless Communication Systems with Conditional GAN as Unknown Channel
- DeepSense: Enabling Carrier Sense in Low-Power Wide Area Networks Using Deep Learning
- Deep unfolding of the weighted MMSE beamforming algorithm
- Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling
- Deep Learning for MIMO Channel Estimation: Interpretation, Performance, and Comparison
- Deep-learning Autoencoder for Coherent and Nonlinear Optical Communication
- Deep Learning in Physical Layer Communications
- Optical Fiber Communication Systems Based on End-to-End Deep Learning
- Machine Learning for Error Correction with Natural Redundancy
- Joint Transceiver Optimization for Wireless Communication PHY with Convolutional Neural Network
- Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning
- Deep Learning Interference Cancellation in Wireless Networks
- Evolution of Physical-Layer Communications Research in the Post-5G Era
- Discriminative Mutual Information Estimators for Channel Capacity Learning
- Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach
- Joint Neural Network Equalizer and Decoder
- Deep-Learning Based Linear Precoding for MIMO Channels with Finite-Alphabet Signaling
- DeepWiPHY: Deep Learning-based Receiver Design and Dataset for IEEE 802.11ax Systems
- Deep Learning based Channel Estimation Algorithm over Time Selective Fading Channels
- Artificial Intelligence-aided Receiver for A CP-Free OFDM System: Design, Simulation, and Experimental Test
- On the Robustness of Deep Learning-aided Symbol Detectors to Varying Conditions and Imperfect Channel Knowledge
- To Learn or Not to Learn: Deep Learning Assisted Wireless Modem Design
- Decision Directed Channel Estimation Based on Deep Neural Network k-step Predictor for MIMO Communications in 5G
- Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
- Deep Learning for Over-the-Air Non-Orthogonal Signal Classification
- Capacity-Approaching Autoencoders for Communications
- Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
- A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
- Quantum-Classical Autoencoder Architectures for End-to-End Radio Communication
- Topological Neural Networks over the Air
- Knowledge-Driven Machine Learning: Concept, Model and Case Study on Channel Estimation
- Framework on Deep Learning Based Joint Hybrid Processing for mmWave Massive MIMO Systems
- ANN-Based Detection in MIMO-OFDM Systems with Low-Resolution ADCs
- Learning to Modulate for Non-coherent MIMO
- DNN-aided Read-voltage Threshold Optimization for MLC Flash Memory with Finite Block Length
- AEVB-Comm: An Intelligent CommunicationSystem based on AEVBs
- Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles
- ELM-based Frame Synchronization in Nonlinear Distortion Scenario Using Superimposed Training
- Unsupervised Learning for Neural Network-based Polar Decoder via Syndrome Loss
- Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
- Supervised-Learning for Multi-Hop MU-MIMO Communications with One-Bit Transceivers
- Neural Communication Systems with Bandwidth-limited Channel
- Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks
- Over-the-fiber Digital Predistortion Using Reinforcement Learning
- A Hybrid Approach combining ANN-based and Conventional Demapping in Communication for Efficient FPGA-Implementation
- Data-Rate Driven Transmission Strategy for Deep Learning Based Communication Systems
- Deep Modulation (Deepmod): A Self-Taught PHY Layer for Resilient Digital Communications
- SVD-Embedded Deep Autoencoder for MIMO Communications
- Integrating Semantic Communication and Human Decision-Making into an End-to-End Sensing-Decision Framework
- Tensor Learning-based Precoder Codebooks for FD-MIMO Systems
- Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel
- A DNN-based OTFS Transceiver with Delay-Doppler Channel Training and IQI Compensation
- Progressive Transmission using Recurrent Neural Networks
- Semantic Communications for Speech Recognition
- Client-Based Intelligence for Resource Efficient Vehicular Big Data Transfer in Future 6G Network
- A Regression Approach to Certain Information Transmission Problems
- Learning Physical-Layer Communication with Quantized Feedback
- Deep Learning for Wireless Communications
- An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels
- User Preference Aware Lossless Data Compression at the Edge
- A Neural Network Aided Approach for LDPC Coded DCO-OFDM with Clipping Distortion
- Model-Driven DNN Decoder for Turbo Codes: Design, Simulation and Experimental Results
- A Generalized Data Representation and Training-Performance Analysis for Deep Learning-Based Communications Systems