Sig-Lime: A Signal-Based Enhancement of Lime Explanation Technique
Interpreting machine learning models is facilitated by the widely employed locally interpretable model-agnostic explanation (LIME) technique. However, when extending LIME to signal data, its credibility falters due to perturbation techniques used to generate local datasets. These techniques disrupt...
保存先:
| 主要な著者: | , , , , , , , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
IEEE
2024-01-01
|
| シリーズ: | IEEE Access |
| 主題: | |
| オンライン・アクセス: | https://ieeexplore.ieee.org/document/10488390/ |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|
