How humans are teaching computers to understand pictures


When a little child looks at a picture, she can identify simple elements: “cat,” “book,” “airplane.”  Now, computers are getting smart enough to do that too. What’s next? Computer scientists are developing powerful new ways to have computers identify what a photograph is showing.

In the above TED talk, Computer vision expert Fei-Fei Li talks about her ImageNet project that has changed how computers see. ImageNet uses a database of 15 million photographs to instruct computers to recognize things in pictures. Li’s team released the dataset to the world for free, and it has since become one of the industry benchmarks in how well computers can perform in recognition.