Microsoft computer identifies objects better than humans

February 15, 2015 1:06 AM

20 0

Humans can identify objects with an error rate of 5.1 percent, but Microsoft's new system only has an error rate of 4.94 percent. It's a small difference, but it's never been done before.

To get these results, the research team out of Beijing had the system analyze ImageNet's 2012 classification dataset, which contains over 1.2 million training images, 50,000 validation images and 100,000 test images.

Read more

To category page