Wednesday, June 27, 2012
Google's 'brain simulator': 16,000 computers to identify a cat
Stanford computer scientist Andrew Ng next to an image of a cat that a neural network taught itself to recognise. Photo: The New York Times
Inside Google's secretive X laboratory, known for inventing self-driving cars and augmented reality glasses, a small group of researchers began working several years ago on a simulation of the human brain.
There Google scientists created one of the largest neural networks for machine learning by connecting 16,000 computer processors, which they turned loose on the internet to learn on its own.
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 recognise 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 recognising objects in a challenging list of 20,000 distinct items.
Jane Burgermeister – Pandemic Update
Jane Burgmeister is an Austrian doctor that has discovered the conspiracies behind the Swine flu and vaccination programs. She has been researching and reporting about this and in the following video, she reports about a variety of stories and builds a case about the state of things.
Subscribe to:
Posts (Atom)