With No Human Supervision, 16,000 Computers Learn to Recognize Cats


Computers learned to recognize cats. Photo: Flickr user MowT

With the aim of simulating the human brain, Google scientists hooked up 16,000 computer processors, creating more than one billion connections, threw 10 million random YouTube thumbnail images at it, and had “the software automatically learning from the data,” as one researcher told The New York Times .

After going through millions of images, the software learned to recognize cats. (This is YouTube, after all.)

As the Times reports, it’s a crazy example of a computer learning information with little human supervision:

“We never told it during the training, ‘This is a cat,’ ” said Dr. Dean, who originally helped Google design the software that lets it easily break programs into many tasks that can be computed simultaneously. “It basically invented the concept of a cat.”

But could a computer invent LOLcats?

More from Smithsonian.com:

Man or Computer? Can You Tell the Difference?

Get the latest stories in your inbox every weekday.