Cargando…
When will AI misclassify? Intuiting failures on natural images
Machine recognition systems now rival humans in their ability to classify natural images. However, their success is accompanied by a striking failure: a tendency to commit bizarre misclassifications on inputs specifically selected to fool them. What do ordinary people know about the nature and preva...
Autores principales: | Nartker, Makaela, Zhou, Zhenglong, Firestone, Chaz |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Association for Research in Vision and Ophthalmology
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10082388/ https://www.ncbi.nlm.nih.gov/pubmed/37022698 http://dx.doi.org/10.1167/jov.23.4.4 |
Ejemplares similares
-
Six ways of failing to see (and why the differences matter)
por: Nartker, Makaela, et al.
Publicado: (2023) -
Humans can decipher adversarial images
por: Zhou, Zhenglong, et al.
Publicado: (2019) -
Survey design and analysis considerations when utilizing misclassified sampling strata
por: Mitani, Aya A., et al.
Publicado: (2021) -
2414: Reperfusion strategies when non-stemi is misclassified as stemi myocardial infarction
por: Altieri, Pablo I., et al.
Publicado: (2018) -
Advancing mathematics by guiding human intuition with AI
por: Davies, Alex, et al.
Publicado: (2021)