Deep Learning Based MIMO Communications

Abstract

We introduce a novel physical layer scheme for single user Multiple-Input Multiple-Output (MIMO) communications based on unsupervised deep learning using an autoencoder. This method extends prior work on the joint optimization of physical layer representation and encoding and decoding processes as a single end-to-end task by expanding transmitter and receivers to the multi-antenna case. We introduce a widely used domain appropriate wireless channel impairment model (Rayleigh fading channel), into the autoencoder optimization problem in order to directly learn a system which optimizes for it. We considered both spatial diversity and spatial multiplexing techniques in our implementation. Our deep learning-based approach demonstrates significant potential for learning schemes which approach and exceed the performance of the methods which are widely used in existing wireless MIMO systems. We discuss how the proposed scheme can be easily adapted for open-loop and closed-loop operation in spatial diversity and multiplexing modes and extended use with only compact binary channel state information (CSI) as feedback.

under journal submission

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Deep Learning-Based Communication Over the Air
• Supervised-Learning-Aided Communication Framework for MIMO Systems with Low-Resolution ADCs
• An Introduction to Deep Learning for the Physical Layer

Cited by in corpus (41)

• Deep Joint Source-Channel Coding for Wireless Image Transmission
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Learning to Detect
• Deep Learning in Mobile and Wireless Networking: A Survey
• Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
• Deep Learning Based Sphere Decoding
• Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
• RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection
• 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-Waveform: A Learned OFDM Receiver Based on Deep Complex-valued Convolutional Networks
• Learning to Detect Anomalous Wireless Links in IoT Networks
• Deep Learning for Massive MIMO CSI Feedback
• DeepTurbo: Deep Turbo Decoder
• The Convergence of Machine Learning and Communications
• Building Encoder and Decoder with Deep Neural Networks: On the Way to Reality
• DeepSense: Enabling Carrier Sense in Low-Power Wide Area Networks Using Deep Learning
• A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
• Joint Transceiver Optimization for Wireless Communication PHY with Convolutional Neural Network
• Learning to Beamform in Heterogeneous Massive MIMO Networks
• Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach
• Realtime Scheduling and Power Allocation Using Deep Neural Networks
• 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
• An Orthogonal-SGD based Learning Approach for MIMO Detection under Multiple Channel Models
• ComNet: Combination of Deep Learning and Expert Knowledge in OFDM Receivers
• A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
• Deep Learning Assisted Antenna Selection in Untrusted Relay Networks
• Sparse Array Beamformer Design for Active and Passive Sensing
• Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
• 5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning
• Relay Selection for 5G New Radio Via Artificial Neural Networks
• Benchmarking End-to-end Learning of MIMO Physical-Layer Communication
• Sparse Array Capon Beamformer Design Availing Deep Learning
• Bit-level Optimized Neural Network for Multi-antenna Channel Quantization
• Hybrid Beamforming/Combining for Millimeter Wave MIMO: A Machine Learning Approach
• SVD-Embedded Deep Autoencoder for MIMO Communications
• An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels
• SNR-adaptive deep joint source-channel coding for wireless image transmission
• Deep Learning for Cross-Technology Communication Design
• Low PAPR waveform design for OFDM SYSTEM based on Convolutional Auto-Encoder