Interpreting 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_ | 1866913377466449920 |
|---|---|
| author | Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos |
| author_facet | Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos |
| contents | Deep learning methods have recently been used to construct non-linear codes for the additive white Gaussian noise (AWGN) channel with feedback. However, there is limited understanding of how these black-box-like codes with many learned parameters use feedback. This study aims to uncover the fundamental principles underlying the first deep-learned feedback code, known as Deepcode, which is based on an RNN architecture. Our interpretable model based on Deepcode is built by analyzing the influence length of inputs and approximating the non-linear dynamics of the original black-box RNN encoder. Numerical experiments demonstrate that our interpretable model -- which includes both an encoder and a decoder -- achieves comparable performance to Deepcode while offering an interpretation of how it employs feedback for error correction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17519 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interpreting Deepcode, a learned feedback code Zhou, Yingyao Devroye, Natasha Turan, Gyorgy Zefran, Milos Information Theory Signal Processing Deep learning methods have recently been used to construct non-linear codes for the additive white Gaussian noise (AWGN) channel with feedback. However, there is limited understanding of how these black-box-like codes with many learned parameters use feedback. This study aims to uncover the fundamental principles underlying the first deep-learned feedback code, known as Deepcode, which is based on an RNN architecture. Our interpretable model based on Deepcode is built by analyzing the influence length of inputs and approximating the non-linear dynamics of the original black-box RNN encoder. Numerical experiments demonstrate that our interpretable model -- which includes both an encoder and a decoder -- achieves comparable performance to Deepcode while offering an interpretation of how it employs feedback for error correction. |
| title | Interpreting Deepcode, a learned feedback code |
| topic | Information Theory Signal Processing |
| url | https://arxiv.org/abs/2404.17519 |