# Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

arXiv: https://arxiv.org/abs/1608.06409 · HTML: https://mlsanity.com/paper/1608.06409/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2016.

## Built on by (most cited first, 13 of 13)

- [ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms](https://mlsanity.com/paper/2112.09559/) (2021)
- [KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning](https://mlsanity.com/paper/2108.12920/) (2021)
- [ProductAE: Towards Training Larger Channel Codes based on Neural Product Codes](https://mlsanity.com/paper/2110.04466/) (2021)
- [Latent Semantic Diffusion-based Channel Adaptive De-Noising SemCom for Future 6G Systems](https://mlsanity.com/paper/2304.09420/) (2023)
- [CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family](https://mlsanity.com/paper/2210.00313/) (2022)
- [ProductAE: Toward Deep Learning Driven Error-Correction Codes of Large Dimensions](https://mlsanity.com/paper/2303.16424/) (2023)
- [Learning Robust Representations for Communications over Noisy Channels](https://mlsanity.com/paper/2409.01129/) (2024)
- [Deep Learning in Wireless Communication Receiver: A Survey](https://mlsanity.com/paper/2501.17184/) (2025)
- [Signal Processing Based Deep Learning for Blind Symbol Decoding and Modulation Classification](https://mlsanity.com/paper/2106.10543/) (2021)
- [Deep Convolutional Learning-Aided Detector for Generalized Frequency Division Multiplexing with Index Modulation](https://mlsanity.com/paper/2202.02876/) (2022)
- [Interpreting Training Aspects of Deep-Learned Error-Correcting Codes](https://mlsanity.com/paper/2305.04347/) (2023)
- [I Can't Believe It's Not Real: CV-MuSeNet: Complex-Valued Multi-Signal Segmentation](https://mlsanity.com/paper/2506.11048/) (2025)
- [Machine Learning for Underwater Optical Wireless Communication Systems: A Comprehensive Survey](https://mlsanity.com/paper/2609.22294/) (2026)

## Abstract (arXiv)

We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel. We treat the problem as reconstruction optimization through impairment layers in a channel autoencoder and introduce several new domain-specific regularizing layers to emulate common channel impairments. We also apply a radio transformer network based attention model on the input of the decoder to help recover canonical signal representations. We demonstrate some promising initial capacity results from this architecture and address several remaining challenges before such a system could become practical.