Printed from http://www.electronista.com

Google X Lab teaches computers to identify faces, cats

updated 03:15 pm EDT, Tue June 26, 2012

1000 machine neural network scanned 10M YouTube images

Google's X Lab has built a one-billion-connection "neural network" that can identify cats on YouTube. The project, aimed at simulating object recognition by humans, was able to more than double the accuracy of item identification from a list of 20,000, according to the New York Times, Using 16,000 cores in 1000 connected machines, the system learned to identify objects without human supervision. The technology represents a departure from current vision-learning methods.

The system was fed 10 million images from YouTube thumbnails, at a resolution of 200x200. After three days of learning, it was able to recognize not only the human face and the human body, but also cats, a subject seen frequently in online video clips. The improved 15.8 percent accuracy rate is said to be a leap of 70 percent over the previous state-of-the-art system.

A presentation of the researchers findings will be presented at a conference in Scotland, and it is likely that Google will capitalize on the research, having previously worked with face-recognition technology.



By Electronista Staff
Post tools:

TAGS :

toggle

Comments

Login Here

Not a member of the MacNN forums? Register now for free.

toggle

Network Headlines

toggle

Most Popular

Sponsor

Recent Reviews

Dell AD211 Bluetooth speaker

For all of the high-priced, over-engineered Bluetooth speakers in the electronics market, there is still room for mass-market solution ...

VisionTek 128GB USB Pocket SSD

USB flash drives dealt the death blow to both the floppy and Zip drives. While still faster than either of the old removable media, sp ...

Kodak PixPro SL10 Smart Lens Camera

Smartphone imagery still widely varies. Large Megapixel counts don't make for a good image, and the optics in some devices are lacking ...

Sponsor

toggle

Most Commented

 
toggle

Popular News