Deepcode: Feedback Codes Via Deep Learning

Authors:
Hyeji Kim Samsung AI Center Cambridge
Yihan Jiang University of Washington Seattle
Sreeram Kannan University of Washington
Sewoong Oh University of Washington
Pramod Viswanath UIUC

Introduction:

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.

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 beats 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.

You may want to know: