Higher-order Interpretations of Deepcode, a Learned Feedback Code
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914920569765888 |
|---|---|
| author | Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos |
| author_facet | Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11907 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Higher-order Interpretations of Deepcode, a Learned Feedback Code Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos Information Theory 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. |
| title | Higher-order Interpretations of Deepcode, a Learned Feedback Code |
| topic | Information Theory |
| url | https://arxiv.org/abs/2408.11907 |