Friday, January 25, 2019

Self-driving cars, robots: Identifying AI 'blind spots'

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
at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Scientists discover a protein switch that burns fat and blocks new fat cells

A protein called “Mitch” may hold the key to a new generation of obesity treatments. Researchers found that disabling it in human cells boos...