Presented with 10 million digital images found in YouTube videos, what did Google’s brain do? What millions of humans do with YouTube: looked for cats. The neural network taught itself to recognize cats, which is actually no frivolous activity. This week the researchers will present the results of their work at a conference in Edinburgh, Scotland. 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.
In a Big Network of Computers, Evidence of Machine Learning - NYTimes.com. For “The neural network taught itself to recognize cats,” read: “The image-recognition software that we wrote and installed on our computers worked much better than we expected it to.” Technologists and tech journalists love to work together to sell these the-Singularity-is-coming stories, even when they don’t mention the SIngularity. And they’re trusting that readers will be so awe-filled that they won’t pause to ask, “What exactly do you mean by ‘taught itself’?”