An Introduction to Deep Learning for the Physical Layer
arXiv:1702.00832
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.
arXiv comment13 pages, 12 figures, 5 tables, under submission to academic journal
References in corpus (23)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Scikit-learn: Machine Learning in Python
- Caffe: Convolutional Architecture for Fast Feature Embedding
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Asynchronous Methods for Deep Reinforcement Learning
- Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- Gradient-based Hyperparameter Optimization through Reversible Learning
- Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
- Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
- Neural Programmer-Interpreters
- Detection Algorithms for Communication Systems Using Deep Learning
- Learning to Protect Communications with Adversarial Neural Cryptography
- Supervised-Learning-Aided Communication Framework for MIMO Systems with Low-Resolution ADCs
- Reinforcement Learning Neural Turing Machines - Revised
- Convolutional Radio Modulation Recognition Networks
- On Deep Learning-Based Channel Decoding
- RNN Decoding of Linear Block Codes
- Learning to Invert: Signal Recovery via Deep Convolutional Networks
- Learning Radio Resource Management in 5G Networks: Framework, Opportunities and Challenges
- Scaling Deep Learning-based Decoding of Polar Codes via Partitioning
- Unsupervised Representation Learning of Structured Radio Communication Signals
Cited by in corpus (8)
- Deep Learning Methods for Improved Decoding of Linear Codes
- Learning to Detect
- Deep Learning Based MIMO Communications
- RNN Decoding of Linear Block Codes
- Optimal Physical Preprocessing for Example-Based Super-Resolution
- AI Coding: Learning to Construct Error Correction Codes
- MIMO Channel Information Feedback Using Deep Recurrent Network
- Bit-level Optimized Neural Network for Multi-antenna Channel Quantization