Researchers from Microsoft claim to have developed a computer system that is actually better than humans at classifying images, which is no small feat. It has been estimated that humans are able to classify ImageNet dataset images with a 5.1% error rate, something that computers have been close to beating so far but have never succeeded, until now that is.
Microsoft researchers claim in a recently published paper that they have developed the first computer system capable of outperforming humans on a popular benchmark. While it’s estimated that humans can classify images in the ImageNet dataset with an error rate of 5.1 percent, Microsoft’s team said its deep-learning-based system achieved an error rate of only 4.94 percent. Their paper was published less than a month after Baidu published a paper touting its record-setting system, which it claimed achieved an error rate of 5.98 percent using a homemade supercomputing architecture. The best performance in the actual ImageNet competition so far belongs to a team of Google researchers, who in the 2014 built a deep learning system with a 6.66 percent error rate.