Mantvydas Lopeta
@mantvydasl.bsky.social
Reposted by Mantvydas Lopeta
The authors point out that AI models base their predictions on sneaky shortcut effects all the time; they're just easier to identify when the conclusions (beer drinking) are clearly spurious.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
The risk of shortcutting in deep learning algorithms for medical imaging research - Scientific Reports
Scientific Reports - The risk of shortcutting in deep learning algorithms for medical imaging research
www.nature.com
December 14, 2024 at 6:02 PM
The authors point out that AI models base their predictions on sneaky shortcut effects all the time; they're just easier to identify when the conclusions (beer drinking) are clearly spurious.
www.nature.com/articles/s41...
www.nature.com/articles/s41...