An AI Learns To Predict Human Behavior By Watching 600 Hours of TV, YouTube

Scientists fed computer with TV shows to predict what humans will do next MIT’s Computer Science and Artificial Intelligence Laboratory created an algorithm that utilizes deep learning, which enables artificial intelligence (AI) to anticipate interactions more accurately than ever before. The researchers developed predictive-vision software that uses machine learning to anticipate what actions should follow a given set of video frames. They fed the program with 600 hours of videos from YouTube and popular TV shows such as Big Bang Theory, The Office and Desperate Housewives to test and see if it can predict whether two people will shake hands, slap five, kiss or hug. In a second situation, the algorithm can anticipate what could appear in a video after five seconds. It searches for patterns and recognizable objects such…


Link to Full Article: An AI Learns To Predict Human Behavior By Watching 600 Hours of TV, YouTube