The team, led by Google’s Dr Jeff Dean, employed the 16,000 processor array to produce a brain-style ‘neural network’ with more than a billion connections.
There is a certain grim inevitability to the reality that the YouTube company’s creation started watching stills from cat videos
The team then fed it random pictures culled from 10 million YouTube videos – and let it ‘learn’ by itself.
Unsurprisingly, the machine focused in on cats.
‘We never told it throughout the instruction, ‘This is a cat,” stated Dr. Dean. ‘It essentially invented the concept of a cat.’
‘Contrary to what appears to be a widely-held intuition, our experimental benefits reveal that it is achievable to train a face detector with no getting to label images as containing a face or not,’ says the team in a paper published this week.
‘We also find that the same network is sensitive to other high-level ideas such as cat faces and human bodies.
Crazy cats!
Sources and more information:
• Google creates ‘artificial brain’ – and it immediately starts watching cat videos
The team, led by Google’s Dr Jeff Dean, used the 16,000 processor array to create a brain-style ‘neural network’ with more than a billion connections. There’s a certain grim inevitability to the fact that the YouTube company’s creation began watching stills from cat videos The team then fed it random images culled from 10 million YouTube videos -…
• Google artificial brain recognizes cat images
In an experiment at Google’s top secret X Laboratory in Mountain View, California, the cyber brain was shown 10 million random images from YouTube and taught itself how to recognize a cat. The scientists working on the project have been very impressed with the results: “We never told it during the training, ‘this is a cat’.
• Google teaching computers to mimic human brain
• Google-built machine learns to find cats on the Internet – msnbc.com
• Google created ‘artificial brain’ and it got addicted to cat videos