LEVAN: software learns anything

​Computer scientists from the University of Washington and the Allen Institute for Artificial Intelligence in Seattle have created LEVAN. Called Learning Everything about Anything, or LEVAN, the computer program searches millions of images and books online to learn all the variations of a concept. LEVAN then displays the results to users helping them explore and understand topics in great detail.

Users are now able to browse an existing library of 175 concepts. So it is just beginning. The current concepts range from “airline” to “window,” and include “beautiful,” “breakfast,” “shiny,” “cancer,” “innovation,” “skateboarding,” “robot,”. The first input into LEVAN is “horse.” If a concept doesn’t exist in LEVAN, anyone can submit a search term and the program will automatically begin generating an exhaustive list of subcategory images that relate to that concept. 

The researchers launched the program in March with only a handful of concepts and have watched it grow since then to tag more than 13 million images with 65,000 different phrases.

For now LEVAN is limited in how fast it can ‘learn’ about a concept. This because of the computational power it takes to process each query. Research is now working on increasing the processing speed and capabilities of LEVAN. The research team wants LEVAN to be both an educational tool as well as an information bank for researchers in the computer vision community. The team also hopes to offer a smartphone app that can run the program to automatically parse out and categorize photos.

More information? See LEVAN.