Featured Articles

Snapdragon 400 is Qualcomm’s SoC for watches, wearables

Snapdragon 400 is Qualcomm’s SoC for watches, wearables

We wanted to learn a bit more about Qualcomm's plans for wearables and it turns out that the company believes its…

More...
Qualcomm sampling 20nm Snapdragon 810

Qualcomm sampling 20nm Snapdragon 810

We had a chance to talk to Michelle Leyden-Li, Senior Director of Marketing, QCT at Qualcomm and get an update on…

More...
EVGA GTX 970 SC ACX 2.0 reviewed

EVGA GTX 970 SC ACX 2.0 reviewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
Nvidia GTX 980 reviewed

Nvidia GTX 980 reviewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
PowerColor TurboDuo R9 285 reviewed

PowerColor TurboDuo R9 285 reviewed

Today we will take a look at the PowerColor TurboDuo Radeon R9 285. The card is based on AMD’s new…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Friday, 22 November 2013 10:16

Computer learns common sense

Written by Nick Farrell



Obviously not an Apple

Scientists at Carnegie Mellon University have built software that can search the web 24 hours a day, seven days a week and from the process learn common sense. Given that we search the web 12 hours a day and we only learned that Kennedy was killed by shape-shifting aliens this is a bit of a surprise.

However the software, dubbed the Never Ending Image Learner (NEIL) and it was designed to search for images and do its best to understand these images on its own. The program runs on two clusters of computers that include 200 processing cores which is a little more than the average human can manage without coffee. As NEIL grows a visual database it is expected to gather common sense on what is being dubbed a “massive scale.”

The designers have already shown some unique findings that could be chalked up to common sense, such as “Deer can be a kind of / look similar to Antelope,” and “Trading Floor can be / can have Crowded.”

Abhinav Gupta, assistant research professor in Carnegie Mellon’s Robotics Institute said that images were the best way to learn visual properties. People learn this by themselves and, with NEIL, we hope that computers will do so too.

Nick Farrell

E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments