# "Machine LLRning": Learning to Softly Demodulate

arXiv: https://arxiv.org/abs/1907.01512 · HTML: https://mlsanity.com/paper/1907.01512/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [DeepTx: Deep Learning Beamforming with Channel Prediction](https://mlsanity.com/paper/2202.07998/) (2022)
- [HybridDeepRx: Deep Learning Receiver for High-EVM Signals](https://mlsanity.com/paper/2106.16079/) (2021)
- [Hybrid Neural Coded Modulation: Design and Training Methods](https://mlsanity.com/paper/2202.01972/) (2022)
- [AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery](https://mlsanity.com/paper/2309.16706/) (2023)
- [Machine Learning-enhanced Receive Processing for MU-MIMO OFDM Systems](https://mlsanity.com/paper/2106.16074/) (2021)
- [Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes](https://mlsanity.com/paper/2506.00368/) (2025)
- [Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems](https://mlsanity.com/paper/2607.08717/) (2026)

## Abstract (arXiv)

Soft demodulation, or demapping, of received symbols back into their conveyed soft bits, or bit log-likelihood ratios (LLRs), is at the very heart of any modern receiver. In this paper, a trainable universal neural network-based demodulator architecture, dubbed "LLRnet", is introduced. LLRnet facilitates an improved performance with significantly reduced overall computational complexity. For instance for the commonly used quadrature amplitude modulation (QAM), LLRnet demonstrates LLR estimates approaching the optimal log maximum a-posteriori inference with an order of magnitude less operations than that of the straightforward exact implementation. Link-level simulation examples for the application of LLRnet to 5G-NR and DVB-S.2 are provided. LLRnet is a (yet another) powerful example for the usefulness of applying machine learning to physical layer design.