Equivariant Transition Matrices for Explainable Deep Learning: A Lie Group Linearization Approach
Deep learning systems deployed in regulated settings require explanations that are accurate and stable under nuisance transformations, yet classical post hoc transition matrices rely on fidelity-only fitting that fails to guarantee consistent explanations under spatial rotations or other group actio...
Guardat en:
| Autors principals: | , , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
MDPI AG
2026-04-01
|
| Col·lecció: | Machine Learning and Knowledge Extraction |
| Matèries: | |
| Accés en línia: | https://www.mdpi.com/2504-4990/8/4/92 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|