DV Hardware - bringing you the hottest news about processors, graphics cards, Intel, AMD, NVIDIA, hardware and technology!

   Home | News submit | News Archives | Reviews | Articles | Howto's | Advertise
 
DarkVision Hardware - Daily tech news
October 23, 2017 
Main Menu
Home
Info
News archives
Articles
Howto
Reviews
 

Who's Online
There are currently 106 people online.

 

Latest Reviews
Jaybird Freedom 2 wireless sport headphones
Ewin Racing Champion gaming chair
Zowie P-TF Rough mousepad
Zowie FK mouse
BitFenix Ronin case
Ozone Rage ST headset
Lamptron FC-10 SE fan controller
ZOWIE G-TF Rough mousepad
 

Follow us
RSS
 

Baidu first to train AI to perform new tasks using zero shot learning

Posted on Friday, April 07 2017 @ 12:25:09 CEST by


While a lot of the artificial intelligence innovations originate from US-based firms, it's easy to forget there are a lot of other firms around the world that are making breakthroughs. Chinese Internet giant Baidu is one of these companies, they have a big AI team working on various projects and they just announced they've managed to train an AI agent to use zero shot learning to solve a problem without having received any prior examples of how to solve such a task.
In the Baidu project, a virtual teacher gave positive or negative feedback to an agent who was responding to commands issued by the teacher. If the agent rightly connected the command with the intended action, it received a reward, and in the case of failure, it was penalized. The agent slowly learned the correct meaning and usage of words. Later, when presented with an unfamiliar command, it was able to extrapolate the correct meaning and fulfill the desired goal, an example of one shot learning. While this whole process took place in a simple 2D maze world, it could likely be extrapolated to vivid 3D environments, and from there to real world settings.
Basically, Baidu first trained an AI agent to understand language through positive and negative reinforcement. Then the AI agent used this knowledge to navigate a 2D maze using natural language commands. That is the novelty here, in this simplistic model, the system can apply past knowledge to perform new tasks. This is a job that comes naturally to humans but remains very hard for machine learning.

Baidu zero shot learning

Via: ExtremeTech



 



 

DV Hardware - Privacy statement
All logos and trademarks are property of their respective owner.
The comments are property of their posters, all the rest © 2002-2017 DM Media Group bvba