Categories
GeekWire

Computer binges on TV to learn human ways

Image: Big Bang Theory
An AI program analyzed this video frame and predicted that these two characters from “The Big Bang Theory” (played by Sara Rue and Johnny Galecki) would kiss. They did. (Credit: Vondrick et al. / MIT)

Researchers have taught a computer to do a better-than-expected job of predicting what characters on TV shows will do, just by forcing the machine to study 600 hours’ worth of YouTube videos.

The experiment could serve as a commentary on the state of research into artificial intelligence, or on the predictability of sitcom plots. It also calls to mind the scenes from countless science-fiction movies where the alien gets up to speed on human culture just by watching TV.

MIT’s Carl Vondrick and his colleagues are due to present the results of their experiment next week at the International Conference on Computer Vision and Pattern Recognition in Las Vegas.

The researchers developed predictive-vision software that uses machine learning to anticipate what actions should follow a given set of video frames. They grabbed thousands of videos showing humans greeting each other, and fed those videos into the algorithm.

To test how much the machine was learning about human behavior, the researchers presented the computer with single frames that showed meet-ups between characters on TV sitcoms it had never seen, including “The Big Bang Theory,” “Desperate Housewives” and “The Office.” Then they asked whether the characters would be hugging, kissing, shaking hands or exchanging high-fives one second afterward.

Get the full story on GeekWire.

By Alan Boyle

Mastermind of Cosmic Log, contributing editor at GeekWire, author of "The Case for Pluto: How a Little Planet Made a Big Difference," president of the Council for the Advancement of Science Writing. Check out "About Alan Boyle" for more fun facts.

Leave a Reply