Computers can Teach us Just About Anything

These days, computers can accomplish just about anything. Now, researchers from the University of Washington and the Allen Institute for Artificial Intelligence in Seattle have developed the first fully automated computer program that allows the development of just about any type of visual concept, via a program, appropriately titled, "Learning Everything About Anything."

This amazing program searches millions of books and images on the web to learn about all possible variations of concepts, resulting in a display of comprehensive list images for its users.

"It is all about discovering associations between textual and visual data," said Ali Farhadi, a UW assistant professor of computer science and engineering, in a news release. "The program learns to tightly couple rich sets of phrases with pixels in images. This means that it can recognize instances of specific concepts when it sees them."

Researchers will present the project and a related paper this month at the Computer Vision and Pattern Recognition annual conference in Columbus, Ohio.

"Major information resources such as dictionaries and encyclopedias are moving toward the direction of showing users visual information because it is easier to comprehend and much faster to browse through concepts. However, they have limited coverage as they are often manually curated. The new program needs no human supervision, and thus can automatically learn the visual knowledge for any concept," added Santosh Divvala, a research scientist at the Allen Institute for Artificial Intelligence and an affiliate scientist at UW in computer science and engineering, in the release.