Computer Binge-Watches TV And Predicts What Happens

Anything that floats your boat

Computer Binge-Watches TV And Predicts What Happens

Postby NobleSavage » Tue Jul 12, 2016 4:59 pm

That is the case for a new algorithm from MIT's Computer Science and Artificial Intelligence Laboratory. Researchers fed the program 600 hours of YouTube videos and television shows like The Office, Desperate Housewives and Scrubs to see if it could learn about and predict certain human interactions — hugs, kisses, high-fives and handshakes.

The algorithm uses an artificial intelligence technique called "deep learning" to create its own understanding of the patterns that make up human interaction. Given raw, unlabeled data, the machine is asked to figure out on its own what is important and what is not. It's a mechanism that humans naturally develop over the course of their lives by picking up clues in the social interactions of those around them.

They fed the computer 600 hrs of TV, but I bet it could make pretty good predictions after about 20 hrs. How hard is it to figure out that:

--If a man and a woman aged within 25 years of each other work together, they'll fuck.
--If a man and a woman aged within 25 years of each other work together, and one of them is the other's supervisor, they'll TOTALLY fuck.
--If the man and the woman fuck, they'll do it at work. A lot. And they'll be caught.
--Teenagers on TV are either murderers, drug addicts, budding sociopaths, or suicidal.
--Men are limited to thinking about sex; women are limited to thinking about expensive and impractical shoes.
--Chick-rock or hip hop musical montages occur approximately every 18 minutes.
--Firefights occur approximately every 25 minutes; soft-core nudity, about every 10 minutes.
--Any picture, video, or text will wind up in the wrong hands.
"Either way, if you do touch their junk, don't treat it like you want your own treated. Treat it WAY Better."

User avatar
Posts: 6913
Joined: Fri May 20, 2005 3:54 pm

Board index Miss Celanie Off Topic

Who is online

Users browsing this forum: No registered users