Cargando…
Unmasking Clever Hans predictors and assessing what machines really learn
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly intelligent behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade...
Autores principales: | Lapuschkin, Sebastian, Wäldchen, Stephan, Binder, Alexander, Montavon, Grégoire, Samek, Wojciech, Müller, Klaus-Robert |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6411769/ https://www.ncbi.nlm.nih.gov/pubmed/30858366 http://dx.doi.org/10.1038/s41467-019-08987-4 |
Ejemplares similares
-
"What is relevant in a text document?": An interpretable machine learning approach
por: Arras, Leila, et al.
Publicado: (2017) -
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
por: Bach, Sebastian, et al.
Publicado: (2015) -
The “Clever Hans Phenomenon” revisited
por: Samhita, Laasya, et al.
Publicado: (2013) -
Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
por: Hägele, Miriam, et al.
Publicado: (2020) -
Realizing the potential of organoids—an interview with Hans Clevers
por: Bartfeld, Sina
Publicado: (2021)