A novel model identifies instances in which autonomous systems have 'learned' from training examples that don't match what's actually happening in the real world. Engineers could use this model to improve the safety of artificial intelligence systems, such as driverless vehicles and autonomous robots.
from Latest Science News -- ScienceDaily http://bit.ly/2FNLKYG
via IFTTT
Friday, January 25, 2019
Self-driving cars, robots: Identifying AI 'blind spots'
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment