Learning to Detect

Abstract

In this paper we consider Multiple-Input-Multiple-Output (MIMO) detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a Detection Network (DetNet) which is specifically designed for the task. The structure of DetNet is obtained by unfolding the iterations of a projected gradient descent algorithm into a network. We compare the accuracy and runtime complexity of the purposed approaches and achieve state-of-the-art performance while maintaining low computational requirements. Furthermore, we manage to train a single network to detect over an entire distribution of channels. Finally, we consider detection with soft outputs and show that the networks can easily be modified to produce soft decisions.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Massive MIMO Systems with Non-Ideal Hardware: Energy Efficiency, Estimation, and Capacity Limits
• Deep Learning-Based Communication Over the Air
• Deep Learning Methods for Improved Decoding of Linear Codes
• Neural Network Detection of Data Sequences in Communication Systems
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Deep Learning Based MIMO Communications
• Detection Algorithms for Communication Systems Using Deep Learning
• Faster Projection in Sphere Decoding
• RNN Decoding of Linear Block Codes
• Learning to Invert: Signal Recovery via Deep Convolutional Networks
• An Introduction to Deep Learning for the Physical Layer
• Optimality of Large MIMO Detection via Approximate Message Passing

Cited by in corpus (65)

• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures
• Learned Conjugate Gradient Descent Network for Massive MIMO Detection
• Deep Learning Based Sphere Decoding
• Deep Learning Methods for Universal MISO Beamforming
• Learning for Detection: MIMO-OFDM Symbol Detection through Downlink Pilots
• Deep Signal Recovery with One-Bit Quantization
• Binary MIMO Detection via Homotopy Optimization and Its Deep Adaptation
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
• LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers
• VPNet: Variable Projection Networks
• Application of Deep Learning to Sphere Decoding for Large MIMO Systems
• Machine Learning for MU-MIMO Receive Processing in OFDM Systems
• ADMM-Net for Communication Interference Removal in Stepped-Frequency Radar
• RC-Struct: A Structure-based Neural Network Approach for MIMO-OFDM Detection
• 25 Years of Signal Processing Advances for Multiantenna Communications
• Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration
• Direction Concentration Learning: Enhancing Congruency in Machine Learning
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• A matrix-inverse-free implementation of the MU-MIMO WMMSE beamforming algorithm
• Detect to Learn: Structure Learning with Attention and Decision Feedback for MIMO-OFDM Receive Processing
• Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis
• Model-Driven Deep Learning for Physical Layer Communications
• Model-Driven Based Deep Unfolding Equalizer for Underwater Acoustic OFDM Communications
• CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity
• Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
• Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels
• A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems
• Deep unfolding of the weighted MMSE beamforming algorithm
• Superiorized Adaptive Projected Subgradient Method with Application to MIMO Detection
• Learning for Integer-Constrained Optimization through Neural Networks with Limited Training
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems
• A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
• Understanding Deep MIMO Detection
• Intelligent Radio Signal Processing: A Survey
• Learning to Beamform in Heterogeneous Massive MIMO Networks
• Hubbard-Stratonovich Detector for Simple Trainable MIMO Signal Detection
• Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach
• Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
• RCNet: Incorporating Structural Information into Deep RNN for MIMO-OFDM Symbol Detection with Limited Training
• A Model-Driven Deep Learning Method for Massive MIMO Detection
• Artificial Intelligence Driven Channel Coding and Resource Optimization for Wireless Networks: A Systematic Survey
• Learning based signal detection for MIMO systems with unknown noise statistics
• Autoregressive Belief Propagation for Decoding Block Codes
• Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
• A DNN Architecture for the Detection of Generalized Spatial Modulation Signals
• Multilevel MIMO Detection with Deep Learning
• Compression and Acceleration of Neural Networks for Communications
• Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
• Constructing Deep Neural Networks with a Priori Knowledge of Wireless Tasks
• Modified EP MIMO Detection Algorithm with Deep Learning Parameters Selection
• Federated Dynamic Neural Network for Deep MIMO Detection
• IMNet: A Learning Based Detector for Index Modulation Aided MIMO-OFDM Systems
• Learning to Estimate RIS-Aided mmWave Channels
• Deep Learning Based Equalizer for MIMO-OFDM Systems with Insufficient Cyclic Prefix
• Training Channel Selection for Learning-based 1-bit Precoding in Massive MU-MIMO
• Channel Type Recognition in Wireless Communications: A Deep Learning Approach
• Channel charting based beamforming
• A Low-Complexity ADMM-based Massive MIMO Detectors via Deep Neural Networks
• End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels
• Deep Reinforcement Learning Aided Monte Carlo Tree Search for MIMO Detection
• Meta Learning-based MIMO Detectors: Design, Simulation, and Experimental Test
• Learning to Search for MIMO Detection
• Deep Learning for CSI Feedback Based on Superimposed Coding
• On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems