Machine Learning: Geometry Ensures More Reliable Results
August 03, 2024
August 03, 2024
WURZBURG, Germany, Aug. 3 (TNSres) -- The University of Wurzburg issued the following news release:
Neural networks are easily disrupted by adversarial attacks. Scientists at the University of Wurzburg and the Technical University of Munich are now developing new methods to make these systems more robust.
Cars that move independently through traffic; software that recognizes malignant changes in the lungs on X-ray images; chat bots that pass demanding entrance exams at . . .
Neural networks are easily disrupted by adversarial attacks. Scientists at the University of Wurzburg and the Technical University of Munich are now developing new methods to make these systems more robust.
Cars that move independently through traffic; software that recognizes malignant changes in the lungs on X-ray images; chat bots that pass demanding entrance exams at . . .