# A Deep Learning Wireless Transceiver with Fully Learned Modulation and Synchronization

## TL;DR

This paper introduces a deep learning wireless transceiver that learns modulation and synchronization end-to-end, achieving high throughput and outperforming existing systems in over-the-air tests with software defined radio.

## Contribution

It presents a novel neural network architecture that supports fully learned modulation and synchronization without manual signal processing, validated through real-world over-the-air experiments.

## Key findings

- Achieves a raw bit-rate of 0.5 Mbps in over-the-air tests
- Supports learning time synchronization automatically
- Outperforms comparable systems in experimental results

## Abstract

In this paper, we present a deep learning based wireless transceiver. We describe in detail the corresponding artificial neural network architecture, the training process, and report on excessive over-the-air measurement results. We employ the end-to-end training approach with an autoencoder model that includes a channel model in the middle layers as previously proposed in the literature. In contrast to other state-of-the-art results, our architecture supports learning time synchronization without any manually designed signal processing operations. Moreover, the neural transceiver has been tested over the air with an implementation in software defined radio. Our experimental results for the implemented single antenna system demonstrate a raw bit-rate of 0.5 million bits per second. This exceeds results from comparable systems presented in the literature and suggests the feasibility of high throughput deep learning transceivers.