Nonsense can make sense to machine-learning models

MIT scientists discover that contemporary deep-learning methods confidently recognize images that are nonsense, which could be concerning for medical and autonomous driving decision-making.

Related Keywords

,Jonas Mueller ,Brandon Carter ,David Gifford ,Artificial Intelligence Laboratory Ph ,National Institutes Of Health ,Artificial Intelligence Laboratory Phd ,Schmidt Futures ,National Institutes ,Siddhartha Jain ,Neural Information Processing ,Mit Csail ,Deep Learning ,Machine Learning Models ,Neural Networks ,Image Recognition ,Overinterpretation ,Medical Diagnostics ,Self Driving Cars ,Autonomous Vehicles ,Ai Decision Making ,Ifar 10 ,Imagenet ,Eep Image Classifiers ,