MIT Researchers Develop Algorithm to Predict Whether Two People Will Shake Hands

Posted on June 21, 2016

CSAIL Handshake Algorithm study

Computer algorithms are now being developed to start predicting very basic aspects of human behavior. Researchers at MIT's Computer Science and Artificial Intelligence Lab (CSAIL) have developed an algorithm designed to predict whether people will hug, kiss, shake hands or high five when they meet.

CSAIL PhD student Carl Vondrick says in a release, "Humans automatically learn to anticipate actions through experience, which is what made us interested in trying to imbue computers with the same sort of common sense. We wanted to show that just by watching large amounts of video, computers can gain enough knowledge to consistently make predictions about their surroundings."

The CSAIL team created an algorithm that can predict "visual representations," which are described as freeze-frames showing different versions of what the scene might look like. The algorithm employs techniques from deep-learning, artificial intelligence that uses neural networks to teach computers to pore over massive amounts of data and find patterns on their own. Each of the algorithm's networks predicts a representation that is classified as one of the four actions — a hug, handshake, high-five, or kiss. The system then merges those actions into one that it uses as its prediction.

The algorithm learned from watching footage of television shows like The Office and The Big Bang Theory. Take a look:



Photo: Carl Vondrick/MIT CSAIL