It takes 16,000 computers working as a brain to tell if a cat is a cat. We know this thanks to an experiment to create a computer brain carried out in the Google X laboratory, where the machine capable of of recognizing felines was created.
The results of the machine learning study won't be released formally until later this week, so for now we must be content with a sneak peek via the New York Times.
The neural network made up of 16,000 processors was let loose on the Internet and given the opportunity to learn. What it learned is what a cat looks like.
There is more to it than that, of course. After all, even a dog knows what a cat looks like. What else does it mean?
Despite being dwarfed by the immense scale of biological brains, the Google research provides new evidence that existing machine learning algorithms improve greatly as the machines are given access to large pools of data.
In their abstract the researchers said that the work will also have benefits for face recognition systems.
"Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not. Control experiments show that this feature detector is robust not only to translation but also to scaling and out-of-plane rotation," it said. "We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies."
You can check out Google's official blog post on the subject, "Using large-scale brain simulations for machine learning and A.I."
This article was originally published on the Inquirer.
Introducing SES Online
Want to view one of the sessions you missed or listen to an especially informative presenter a second time? SES New York sessions are available for purchase on ClickZ Academy's new e-Learning site. SES is now Online!