Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910963629817856 |
|---|---|
| author | Tuononen, Marko Korpi, Dani Hautamäki, Ville |
| author_facet | Tuononen, Marko Korpi, Dani Hautamäki, Ville |
| contents | We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of the interest, providing insights at both global and local levels -- with global explanations aggregating local ones. Experiments on link-level simulations demonstrate the method's effectiveness in identifying units that contribute most (and least) to signal-to-noise ratio processing. Although we focus on a radio receiver model, the method generalizes to other neural network architectures and applications, offering robust estimation even in high-dimensional settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16768 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios Tuononen, Marko Korpi, Dani Hautamäki, Ville Machine Learning Networking and Internet Architecture Signal Processing 68T07 I.2.6; C.2.1 We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of the interest, providing insights at both global and local levels -- with global explanations aggregating local ones. Experiments on link-level simulations demonstrate the method's effectiveness in identifying units that contribute most (and least) to signal-to-noise ratio processing. Although we focus on a radio receiver model, the method generalizes to other neural network architectures and applications, offering robust estimation even in high-dimensional settings. |
| title | Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios |
| topic | Machine Learning Networking and Internet Architecture Signal Processing 68T07 I.2.6; C.2.1 |
| url | https://arxiv.org/abs/2409.16768 |