Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels
This work addresses the challenge of automated channel coding design for communication systems, particularly in non-canonical scenarios where optimal codes are lacking, representing a novel application of deep learning rather than an incremental improvement.
The authors tackled the problem of designing optimal channel codes for non-canonical communication settings by developing Turbo Autoencoder (TurboAE), a fully end-to-end neural encoder and decoder, which approaches state-of-the-art performance under canonical channels and outperforms existing codes in non-canonical settings in terms of reliability.
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.