Tech content trusted by users in North America and around the world
6,801 Reviews & Articles | 46,981 News Posts
Make us an awesome TweakTown wallpaper, win a Corsair Hydro H110i GT

Google X Lab teaches computers to identify faces, oh, and cats, too

Google X Lab has been working hard, have created a 1000 machine neural network that has scanned 10 m
| Cloud Computing News | Posted: Jun 27, 2012 11:19 am

We're seeing the beginnings of Skynet, with Intel working on launching technology that mimics the human brain and "learns" of its user, but the Google X Lab has built a one-billion-connection "neural network" that can identify... cats... on YouTube. Yes, cats.




The project did have an aim, where it looked to simulate object recognition by humans, and was able to more than double the accuracy of item identification from a list of 20,000. Using 16,000 cores in 1000 connected machines (is that all?), the system was able to identify objects, all without human supervision.


The technology represents a big departure from current vision-learning methods. The system was fed 10 million images from YouTube thumbnails, at the low resolution of 200x200. After 72 hours of learning, the system was capable of recognizing not only the human face and body, but also cats, a subject seen frequently on video clips.


The improved 15.8-percent accuracy rate is said to be a jump of over 70-percent from the previous state-of-the-art system.


Related Tags

Got an opinion on this news? Post a comment below!
Subscribe to our Newsletter

Latest News Posts

View More News Posts

Forum Activity

View More Forum Posts

Press Releases

View More Press Releases