Cargando…

Scrutinizing XAI using linear ground-truth data with suppressor variables

Machine learning (ML) is increasingly often used to inform high-stakes decisions. As complex ML models (e.g., deep neural networks) are often considered black boxes, a wealth of procedures has been developed to shed light on their inner workings and the ways in which their predictions come about, de...

Descripción completa

Detalles Bibliográficos
Autores principales: Wilming, Rick, Budding, Céline, Müller, Klaus-Robert, Haufe, Stefan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9123083/
https://www.ncbi.nlm.nih.gov/pubmed/35611184
http://dx.doi.org/10.1007/s10994-022-06167-y