Higher-order Interpretations of Deepcode, a Learned Feedback Code
Information Theory
2024-08-23 v1 math.IT
Abstract
We present an interpretation of Deepcode, a learned feedback code that showcases higher-order error correction relative to an earlier interpretable model. By interpretation, we mean succinct analytical encoder and decoder expressions (albeit with learned parameters) in which the role of feedback in achieving error correction is easy to understand. By higher-order, we mean that longer sequences of large noise values are acted upon by the encoder (which has access to these through the feedback) and used in error correction at the decoder in a two-stage decoding process.
Cite
@article{arxiv.2408.11907,
title = {Higher-order Interpretations of Deepcode, a Learned Feedback Code},
author = {Yingyao Zhou and Natasha Devroye and Gyorgy Turan and Milos Zefran},
journal= {arXiv preprint arXiv:2408.11907},
year = {2024}
}
Comments
accepted to 60th Annual Allerton Conference