Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

TL;DR

This paper introduces Turbo Autoencoder, a deep learning-based neural coding scheme that achieves near-optimal performance in both canonical and non-canonical communication channels, automating channel code design.

Contribution

The paper presents Turbo Autoencoder, a novel end-to-end neural encoder-decoder that outperforms existing codes in various channel settings, including non-canonical channels.

Findings

TurboAE approaches state-of-the-art performance in canonical channels.

TurboAE outperforms existing codes in non-canonical channels.

Deep learning can automate the development of effective channel codes.

Abstract

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians for communicating under canonical models after over 60 years of research. On the other hand, in many non-canonical channel settings, optimal codes do not exist and the codes designed for canonical models are adapted via heuristics to these channels and are thus not guaranteed to be optimal. In this work, we make significant progress on this problem by designing a fully end-to-end jointly trained neural encoder and decoder, namely, Turbo Autoencoder (TurboAE), with the following contributions: ($a$) under moderate block lengths, TurboAE approaches state-of-the-art performance under canonical channels; ($b$) moreover, TurboAE outperforms the state-of-the-art codes under non-canonical settings in terms of reliability. TurboAE shows that the development of channel coding design can be automated via deep learning, with near-optimal performance.