Google created an artificial intelligence system with a staggering 16,000 processors and let the thing loose on the internet to learn on its own. And what did it learn? CATS. "The musical?" *stink-eye*
The neural network taught itself to recognize cats, which, John Markoff of The New York Times reports, is actually no frivolous activity. This week the researchers will present the results of their work at a conference in Edinburgh. The Google scientists and programmers will note that while it is hardly news that the Internet is full of cat videos, the simulation nevertheless surprised them. It performed far better than any previous effort by roughly doubling its accuracy in recognizing objects in a challenging list of 20,000 distinct items.
Impressive. And I'm not just saying that because sometimes I see a cat picture and think it's a dog, but seriously sometimes they're hard to tell apart. *Googling* Like this one -- is that a cat or a dog? "That's a turtle." Really? Is there an easy way to tell?
Thanks to Mnemosyne, Bradley and Samuel D, who agree there were really only three learning possibilities: cats, p0rn, or trolling.