Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks
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_ | 1866910720539492352 |
|---|---|
| author | Fischer, Rodrigo Matalla, Patrick Randel, Sebastian Schmalen, Laurent |
| author_facet | Fischer, Rodrigo Matalla, Patrick Randel, Sebastian Schmalen, Laurent |
| contents | We investigate Kolmogorov-Arnold networks (KANs) for non-linear equalization of 112 Gb/s PAM4 passive optical networks (PONs). Using pruning and extensive hyperparameter search, we outperform linear equalizers and convolutional neural networks at low computational complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19631 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks Fischer, Rodrigo Matalla, Patrick Randel, Sebastian Schmalen, Laurent Signal Processing Machine Learning We investigate Kolmogorov-Arnold networks (KANs) for non-linear equalization of 112 Gb/s PAM4 passive optical networks (PONs). Using pruning and extensive hyperparameter search, we outperform linear equalizers and convolutional neural networks at low computational complexity. |
| title | Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2411.19631 |