MIT Neural Net Predicts What Happens Next on TV Shows

Most Popular Created with Sketch. Jun 21, 2016 Researchers at MIT have developed an algorithm that will allow an artificial intelligence to predict what it will see next. It’s a major step forward in the field of robotic predictive vision. How did the algorithm learn to predict human interactions? By watching TV, of course. Using deep-learning techniques to create neural nets that MIT has already used to train robots to recreate sounds, researchers at Computer Science and Artificial Intelligence Laboratory (CSAIL) sat their algorithm in front of Desperate Housewives and The Office as well as various YouTube videos. It watched more than 600 hours of video, with researchers hoping that it would be able to predict four basic motions: a hug, a kiss, shaking hands, or a high five. Advertisement – Continue Reading Below Predictive vision has previously been based on pixel-based interpretations of what…


Link to Full Article: MIT Neural Net Predicts What Happens Next on TV Shows