Googles artificial Brain teaches itself how to find Cats on the Web

Google X, das experimentelle Labor, in dem sie die Google Brillen und die Robo-Autos entwickeln, hat ein neuronales Netz aus 16.000 Prozessoren aufgebaut und das Ding mit 10 Millionen zufälligen Thumbnails aus Youtube-Videos gefüttert. Dieses Netz hat daraus das Konzept „Katze“ entwickelt, völlig autonom und ohne Anleitung von außen: Googles Hirnsimulation hat gelernt, was eine Katze ist. Ich meine, da hat man ein künstliches Hirn und schmeisst es zu mit Daten und was macht es? Katzen!

To find them, the Google research team, lead by the Stanford University computer scientist Andrew Y. Ng and the Google fellow Jeff Dean, used an array of 16,000 processors to create a neural network with more than one billion connections. They then fed it random thumbnails of images, one each extracted from 10 million YouTube videos.

The videos were selected randomly and that in itself is an interesting comment on what interests humans in the Internet age. However, the research is also striking. That is because the software-based neural network created by the researchers appeared to closely mirror theories developed by biologists that suggest individual neurons are trained inside the brain to detect significant objects. […]

“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.”

How Many Computers to Identify a Cat? 16,000