Hidden away within Google's X laboratory, where all kinds of secret projects are underway, its engineers have been working on creating an artificial brain. With 16,000 computer processors and freedom to learn whatever it chooses from the internet, though, it turns out that the brain does just what you do online: watch cat videos.
The project has produced one of the largest neural networks ever created. The idea is that such technology can take data sets and notice patterns and trends with them, all by itself. But when presented with a data set of 10 million digital images found in YouTube videos, it decided to, umm, learn how to identify cats. From the New York Times:
"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. We probably have other ones that are side views of cats."
The Google brain assembled a dreamlike digital image of a cat by employing a hierarchy of memory locations to successively cull out general features after being exposed to millions of images. The scientists said, however, that it appeared they had developed a cybernetic cousin to what takes place in the brain's visual cortex.
While it's comical to think that one of the world's biggest artificial brains enjoys identifying cats, it's actually no mean feat—and of course is shaped to an extent by the huge number of cat videos present in any random sample of YouTube videos.
What's most impressive, though, is that the technology has managed to develop a system which is comparable to the visual cortex, albeit one millions times smaller than that within a human brain. One of the researchers, however, told the New York Times that "the scale of modeling the full human visual cortex may be within reach before the end of the decade." Maybe by that point it will be a little more discerning over the content it enjoys. [arXiv via New York Times]