Google made an artifical brain by linking together 16,000 computers with 1,000,000,000 connections (a fraction of a normal brain, but what the heck) and set it loose on YouTube. Over a couple of days of constant work, the artificial brain learned to recognize various things including cats.
Picking up on the most commonly occurring images featured on YouTube, the system achieved 81.7 percent accuracy in detecting human faces, 76.7 percent accuracy when identifying human body parts and 74.8 percent accuracy when identifying cats.
“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,” the team says in its paper, Building high-level features using large scale unsupervised learning, which it will present at the International Conference on Machine Learning in Edinburgh, 26 June-1 July.
What I want to know is this: If I put a kitty cat on every one of my blog posts will I get more hits???