commonsense
Latest
Carnegie Mellon computer learns common sense through pictures, shows what it's thinking
Humans have a knack for making visual associations, but computers don't have it so easy; we often have to tell them what they see. Carnegie Mellon's recently launched Never Ending Image Learner (NEIL) supercomputer bucks that trend by forming those connections itself. Building on the university's earlier NELL research, the 200-core cluster scours the internet for images and defines objects based on the common attributes that it finds. It knows that buildings are frequently tall, for example, and that ducks look like geese. While NEIL is occasionally prone to making mistakes, it's also transparent -- a public page lets you see what it's learning, and you can suggest queries if you think there's a gap in the system's logic. The project could eventually lead to computers and robots with a much better understanding of the world around them, even if they never quite gain human-like perception.
Common sense training on the DS
Forget training your brain -- what most people need is to learn not to be a complete moron in day to day life. But they don't mean common sense in the "don't set yourself on fire because it's funny" way (which is a shame), but common sense in the "general knowledge" way. Famitsu has several new screens from the third installment in the DS Touch Generations training series, but darned if we can tell what's going on in all of them. Maybe we need a little training.There's been some dispute over the translation of the title, so until we get an English version, we'll just go with Otona No Joushikiryoku Training DS. The game is scheduled for a Japanese release in October.Who can tell us what kind of flowers those are?[Via Go Nintendo]
