Breaking AIs to make them better
Current AIs are very accurate but inflexible at image recognition. Exactly why this is remains a mystery. Researchers have developed a method called 'Raw Zero-Shot' to assess how neural networks handle elements unknown to them. The results have the potential to help researchers identify the common features that make neural networks 'non-robust,' and develop methods to make AIs more reliable.
from Latest Science News -- ScienceDaily https://ift.tt/p8EHwU3
from Latest Science News -- ScienceDaily https://ift.tt/p8EHwU3
Comments
Post a Comment