Heather Monk Blog
Wednesday, December 20, 2017
Researchers Made Google's Image Recognition AI Mistake a Rifle For a Helicopter
To safeguard AI, we’re going to need to solve the problem of ‘adversarial examples.’
from
https://www.wired.com/story/researcher-fooled-a-google-ai-into-thinking-a-rifle-was-a-helicopter
No comments:
Post a Comment
Newer Post
Older Post
Home
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment