System designed to label visual scenes according to type turns out to detect particular objects, too

http://newsoffice.mit.edu/2015/visual-scenes-object-recognition-0508

The most fascinating section to me:

“Deep learning works very well, but it’s very hard to understand why it works — what is the internal representation that the network is building,” says Antonio Torralba, an associate professor of computer science and engineering at MIT and a senior author on the new paper. “It could be that the representations for scenes are parts of scenes that don’t make any sense, like corners or pieces of objects. But it could be that it’s objects: To know that something is a bedroom, you need to see the bed; to know that something is a conference room, you need to see a table and chairs. That’s what we found, that the network is really finding these objects.”

I suspect the road to full general A.I. will be littered with many such "we don't know how it's doing this" sentiments.