The world's first artificial neural network has spent its first days of existence doing the same thing as millions of bored office workers... looking at cats on the internet.

The Google research team behind the network - 1000 computers wired together to mimic a biological brain - said it taught itself to recognise cats out of millions of YouTube videos it was fed.

"Our hypothesis was that it would learn to recognise common objects in those videos," the researchers said.

"Indeed, to our amusement, one of our artificial neurons learned to respond strongly to pictures of ... cats."


"This network had never been told what a cat was, nor was it given even a single image labelled as a cat."

The computer, essentially, discovered for itself what a cat looked like. The cat-spotting computer was created as part of a larger project to investigate machine learning.

Google is planning to use the learning system to help with its indexing systems and with language translation.

The artificial neural network was put together by Google scientists and Professor Andrew Ng, head of the artificial intelligence lab at Stanford University, California.

The researchers were reluctant to speculate how closely their creation resembled biology.

For instance, they said, their computer system might push the limits of current work on neural networks but it was dwarfed by the complexity of the human visual processing system.

The positive results were a surprise, and ran counter to the intuition that learning could not take place when so little context and guidance was given, they said.

As well as spotting cats, the computer system also learned how to pick out the shape of the human body and to recognise human faces.


- staff reporter