DeepMind Now Learns from Human Preferences, Just Like a Toddler

http://ift.tt/2sMevhS

By New Scientist

June 19, 2017

Comments

Toddler learning

Feedback speeds along learning.

Credit: Adam Hester/Getty

AI systems continue to get increasingly powerful, but still need far too much hand-holding by their human masters. New research from DeepMind and OpenAI suggests a mere nudge here and there at the outset can be enough to help artificial intelligence accomplish tricky tasks.

From New Scientist
View Full Article


 

No entries found

from Communications of the ACM: Artificial Intelligence http://ift.tt/2stwt5A

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s