Researchers Create Computer Program That Teaches Itself 'Everything About Anything'
Researchers from the university of Washington and the Allen Institute for Artificial Intelligence in Seattle have developed the first fully automated computer program that teaches everything there is to know about any visual concept.
The program dubbed 'Learning Everything about Anything' searches millions of books and images on the web and learns all possible variations of a concept. Then it displays the resuls to users as a comprehensive, browsable list of images.
"It is all about discovering associations between textual and visual data," said Ali Farhadi, a UW assistant professor of computer science and engineering, in the press 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," said 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 press release.