It’s only a matter of time before things go the way of Skynet, and this new algorithm is a stepping stone along the way: it can learn to identify objects all by itself, with zero human help. Gulp.
Created by Brigham Young University researchers, this new recognition algorithm churns through images, defining its own parameters with which to define objects. BYU explains how it works:
Instead of trying to explain the difference, we show children images of the animals and they learn on their own to distinguish the two. Lee’s object recognition does the same thing: Instead of telling the computer what to look at to distinguish between two objects, they simply feed it a set of images and it learns on its own.
The research, published in Pattern Recognition, shows that the algorithm performs better than most top object recognition algorithms developed by other universities and private companies, proving to be 95-98 accuracy on data sets including everything from fish to aeroplanes. Who needs humans anyway? [BYU via Slashgear]