DeepCode: Feedback codes via deep learning

Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly outperforms state-of-the-art codes designed over several decades of research. The communication channel under consideration is the Gaussian noise channel with feedback, whose study was initiated by Shannon; feedback is known theoretically to improve reliability of communication, but no practical codes that do so have ever been successfully constructed. We break this logjam by integrating information theoretic insights harmoniously with recurrent-neural-network based encoders and decoders to create novel codes that outperform known codes by 3 orders of magnitude in reliability and achieve a 3dB gain in terms of SNR. We also demonstrate several desirable properties of the codes: (a) generalization to larger block lengths, (b) composability with known codes, and (c) adaptation to practical constraints. This result also has broader ramifications for coding theory: even when the channel has a clear mathematical model, deep learning methodologies, when combined with channel-specific information-theoretic insights, can potentially beat state-of-the-art codes constructed over decades of mathematical research.

Original languageEnglish (US)
Article number2986752
Pages (from-to)194-206
Number of pages13
JournalIEEE Journal on Selected Areas in Information Theory
Volume1
Issue number1
DOIs
StatePublished - May 2020
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Media Technology
  • Artificial Intelligence
  • Applied Mathematics

Keywords

  • Channel coding
  • Deep learning
  • Feedback communication
  • Neural networks
  • Recurrent neural networks
  • Schalkwijk–Kailath scheme

Fingerprint

Dive into the research topics of 'DeepCode: Feedback codes via deep learning'. Together they form a unique fingerprint.

Cite this