Advertisement

ICYMI: Deep learning computers decode human interactions

A vision system watched 600 hours of TV to learn when two people are going to hug.

Today on In Case You Missed It: MIT researchers made a deep learning vision system watch TV and it learned to predict when people are going to kiss, shake hands, high five or hug. Georgia Tech scientists teamed up with others to figure out how to create 3D images of microscopic cells, by giving them a selfie mirror.

To check out the WalMart fireworks video in full, click here. As always, please share any interesting tech or science videos you find by using the #ICYMI hashtag on Twitter for @mskerryd.