AAPL Stock: 117.81 ( -0.22 )

Printed from

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 MacNN Staff



Login Here

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


Network Headlines

Follow us on Facebook


Most Popular


Recent Reviews

Ultimate Ears Megaboom Bluetooth Speaker

Ultimate Ears (now owned by Logitech) has found great success in the marketplace with its "Boom" series of Bluetooth speakers, a mod ...

Kinivo URBN Premium Bluetooth Headphones

We love music, and we're willing to bet that you do, too. If you're like us, you probably spend a good portion of your time wearing ...

Jamstik+ MIDI Controller

For a long time the MIDI world has been dominated by keyboard-inspired controllers. Times are changing however, and we are slowly star ...


Most Commented