# Trainable Communication Systems: Concepts and Prototype

arXiv: https://arxiv.org/abs/1911.13055 · HTML: https://mlsanity.com/paper/1911.13055/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2019.

## Built on by (most cited first, 22 of 22)

- [Waveform Learning for Next-Generation Wireless Communication Systems](https://mlsanity.com/paper/2109.00998/) (2021)
- [Graph Neural Networks for Channel Decoding](https://mlsanity.com/paper/2207.14742/) (2022)
- [Trimming the Fat from OFDM: Pilot- and CP-less Communication with End-to-end Learning](https://mlsanity.com/paper/2101.08213/) (2021)
- [Bit Error and Block Error Rate Training for ML-Assisted Communication](https://mlsanity.com/paper/2210.14103/) (2022)
- [Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications](https://mlsanity.com/paper/2401.12800/) (2024)
- [End-to-End Learning of OFDM Waveforms with PAPR and ACLR Constraints](https://mlsanity.com/paper/2106.16039/) (2021)
- [Concatenated Classic and Neural (CCN) Codes: ConcatenatedAE](https://mlsanity.com/paper/2209.01701/) (2022)
- [End-to-end Waveform Learning Through Joint Optimization of Pulse and Constellation Shaping](https://mlsanity.com/paper/2106.15158/) (2021)
- [Learning OFDM Waveforms with PAPR and ACLR Constraints](https://mlsanity.com/paper/2110.10987/) (2021)
- [Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding](https://mlsanity.com/paper/2110.12059/) (2021)
- [End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model](https://mlsanity.com/paper/2107.12320/) (2021)
- [End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping](https://mlsanity.com/paper/2112.05050/) (2021)
- [Hybrid Neural Coded Modulation: Design and Training Methods](https://mlsanity.com/paper/2202.01972/) (2022)
- [Discriminative Mutual Information Estimators for Channel Capacity Learning](https://mlsanity.com/paper/2107.03084/) (2021)
- [DUIDD: Deep-Unfolded Interleaved Detection and Decoding for MIMO Wireless Systems](https://mlsanity.com/paper/2212.07816/) (2022)
- [Optimizing Serially Concatenated Neural Codes with Classical Decoders](https://mlsanity.com/paper/2212.10355/) (2022)
- [Component Training of Turbo Autoencoders](https://mlsanity.com/paper/2305.09216/) (2023)
- [EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver](https://mlsanity.com/paper/2602.11834/) (2026)
- [Machine Learning-enhanced Receive Processing for MU-MIMO OFDM Systems](https://mlsanity.com/paper/2106.16074/) (2021)
- [Learning Quantization in LDPC Decoders](https://mlsanity.com/paper/2208.05186/) (2022)
- [A Hybrid Approach combining ANN-based and Conventional Demapping in Communication for Efficient FPGA-Implementation](https://mlsanity.com/paper/2304.05042/) (2023)
- [Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes](https://mlsanity.com/paper/2506.00368/) (2025)

## Abstract (arXiv)

We consider a trainable point-to-point communication system, where both transmitter and receiver are implemented as neural networks (NNs), and demonstrate that training on the bit-wise mutual information (BMI) allows seamless integration with practical bit-metric decoding (BMD) receivers, as well as joint optimization of constellation shaping and labeling. Moreover, we present a fully differentiable neural iterative demapping and decoding (IDD) structure which achieves significant gains on additive white Gaussian noise (AWGN) channels using a standard 802.11n low-density parity-check (LDPC) code. The strength of this approach is that it can be applied to arbitrary channels without any modifications. Going one step further, we show that careful code design can lead to further performance improvements. Lastly, we show the viability of the proposed system through implementation on software-defined radios (SDRs) and training of the end-to-end system on the actual wireless channel. Experimental results reveal that the proposed method enables significant gains compared to conventional techniques.