[Pic: An image of a cat that a neural network taught itself to recognize. Source: New York Times]

The internet is obsessed with cats. Completely and utterly obsessed. In Google’s secretive X labratory, scientists have developed one of the largest neural networks for machine learning by connecting 16,000 computer processors. What did it do? Watched Youtube, and worked out what a cat is.

The neural network taught itself to recognize a cat, which is far more complex than it sounds. The researchers fed it random thumbnails of images, one each extracted from 10 million YouTube videos. What’s fascinating, and slightly scary, is that the software-based neural network appeared to closely mirror theories developed by biologists that suggest individual neurons are trained inside the brain to detect significant objects.

The New York Times reports that

Currently much commercial machine vision technology is done by having humans “supervise” the learning process by labeling specific features. In the Google research, the machine was given no help in identifying features.

“The idea is that instead of having teams of researchers trying to find out how to find edges, you instead throw a ton of data at the algorithm and you let the data speak and have the software automatically learn from the data,” Dr. Ng [Stanford University computer scientist, and research team leader] said.

“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.

Before you start worrying about the machine uprising, and sentient computers, remember that our brain is still a far larger, more complex machine. The researchers wrote that their “network is still tiny compared to the human visual cortex, which is a million times larger in terms of the number of neurons and synapses.” Again, I am in awe of our brain, which is a million times bigger than an array of computers that has more than 1 billion connections.

Don’t relax too much though,  David A. Bader, executive director of high-performance computing at the Georgia Tech College of Computing says: “The scale of modeling the full human visual cortex may be within reach before the end of the decade.”

So in our life times we may see an army of computers rise up, sentient machines, thinking robots. I would normally be terrified by such thoughts, however, I am calmed by one thing, we know their weakness: LOLcats.

[Source: New York Times]