# "Machine LLRning": Learning to Softly Demodulate

## TL;DR

This paper introduces LLRnet, a neural network-based soft demodulator that improves performance and reduces complexity in symbol demapping for modern communication systems like 5G and DVB-S.2.

## Contribution

The paper presents LLRnet, a novel trainable neural network architecture for soft demodulation that approaches optimal inference with significantly fewer operations.

## Key findings

- LLRnet achieves near-optimal LLR estimates for QAM.
- LLRnet reduces computational complexity by an order of magnitude.
- Demonstrated effectiveness in 5G-NR and DVB-S.2 simulations.

## Abstract

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.