The Never Ending Image Learner, or NEIL, is a computer at Carnegie Mellon University in Pittsburgh, Pa., that is teaching itself common sense.
NEIL, which is constantly left running, spends it time looking at images to help build up its common sense. The computer has already viewed over three million images and is able to make several connections that normal computer could not. An example of this, which may seem easy to understand as a human, is that NEIL can make a connection between a tiger and a zebra due to the fact that they both have stripes. The computer is able to make several other comparisons and learns more as it scans images. Scientist also hope to have NEIL scanning videos in the future, reports Science Recorder.
NEIL is funded by Google (GOOG) and the Department of Defense’s Office of Naval Research and is still in its beginning stages. It’s unknown why either of these groups is funding the project, but its possible that the technology could be helpful on the battlefield in the future, Science Reporter notes.
“It’s building upon a lot of work in computer vision using deformable part models,” Abhinav Gupta, an assistant research professor at Carnegie Mellon University, told The Register.