Cargando…
Improving Performance of the PRYSTINE Traffic Sign Classification by Using a Perturbation-Based Explainability Approach
Model understanding is critical in many domains, particularly those involved in high-stakes decisions, e.g., medicine, criminal justice, and autonomous driving. Explainable AI (XAI) methods are essential for working with black-box models such as convolutional neural networks. This paper evaluates th...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8874740/ https://www.ncbi.nlm.nih.gov/pubmed/35200732 http://dx.doi.org/10.3390/jimaging8020030 |