Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation.
Davor Vukadin|Petar Afric|Marin Silic|Goran Delac
| Anthology ID: | DBLP:journals/tist/VukadinASD24 |
|---|---|
| Year: | 2024 |
| Venue: | ACM Transactions on Intelligent Systems and Technology (TIST) |
| Pages: | 47:1-47:30 |
| URL: | https://doi.org/10.1145/3649458 |
| DOI: | https://doi.org/10.1145/3649458 |
| DBLP: | journals/tist/VukadinASD24 |
| BibTeX: |
@article{vukadin-2024-advancing,
author = {Davor Vukadin and
Petar Afric and
Marin Silic and
Goran Delac},
title = {{Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation}},
journal = {ACM Transactions on Intelligent Systems and Technology (TIST)},
volume = {15},
number = {3},
pages = {47:1--47:30},
year = {2024},
url = {https://doi.org/10.1145/3649458},
doi = {https://doi.org/10.1145/3649458}
}