Radio Machine Learning Papers 

An Introduction to Machine Learning Communications Systems An in depth overview of communications system and sensing applications of ML to comms.


Communication System PHY Learning

Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention The fundamentals of posing an autoencoder as a communications system.

On Deep Learning-Based Channel Decoding Work looking into the error correction decoding capacity of deep neural networks.

Scaling Deep Learning-based Decoding of Polar Codes via Partitioning Efforts to scale learned decoding techniques for Polar Codes to larger block sizes!

RNN Decoding of Linear Block Codes RNN Decoding comparisons to BP decoders along with interesting complexity comparisons.

Learning to Decode Linear Codes Using Deep Learning E Nachmani, Y Beery, D Burshtein arXiv preprint arXiv:1607.04793


Radio Sensing

Convolutional Radio Modulation Recognition Networks Modulation Recognition from a supervised learning standpoint.

Wireless Interference Identification with Convolutional Neural Networks Using a similar CNN classifier technique to identify 802.11 PHY variants over the air quite successfully.

Semi-Supervised Radio Signal Identification Scaling RF labeling beyond supervised datasets.

Rigorous Moment-Based Automatic Modulation Classification Using DNNs on top of well regarded moment based features for modulation classification.

Deep architectures for modulation recognition NE WestT O'Shea - Dynamic Spectrum Access Networks ( …, 2017 -

Learning and Visualizing Modulation Discriminative Radio Signal Features M Walton, D Gebhardt, B Migliori, L Straatemeier - 2016 -

USRP N210 demonstration of wideband sensing and blind hierarchical modulation classification M LaghateS Chaudhari… - Dynamic Spectrum Access …, 2017 

Modulation recognition with GNU radio, keras, and HackRF  JL Ziegler, RT Arn, W Chambers - Dynamic Spectrum Access …, 2017 

Modulation recognition using hierarchical deep neural networks K Karra, S Kuzdeba, J Petersen - Dynamic Spectrum Access …, 2017 

Electrosense: Crowdsourcing spectrum monitoring B Van den Bergh, D Giustiniano… - Dynamic Spectrum …, 2017 

Spectrum Monitoring for Radar Bands using Deep Convolutional Neural Networks A Selim, F Paisana, JA Arokkiam, Y Zhang… - arXiv preprint arXiv: …, 2017 

Deep Sensing: Cooperative Spectrum Sensing Based on Convolutional Neural Networks W Lee, M Kim, DH ChoR Schober - arXiv preprint arXiv:1705.08164, 2017 

Phasma: An automatic modulation classification system based on Random Forest K Triantafyllakis, M Surligas, G Vardakis… - Dynamic Spectrum …, 2017


Radio Structure Learning

Unsupervised Representation Learning of Structured Radio Communications Signals Unsupervised structure learning from radio datasets

Radio Transformer Networks: Attention Models for Learning to Synchronize in Wireless Systems Augmenting learning models with just-enough expert knowledge of the physical world.