When a very young child looks at a picture, she can identify simple elements: "cat," "book," "chair." Now, computers are getting smart enough to do that too. What's next? In a thrilling talk, computer vision expert Fei-Fei Li describes the state of the art  -- including the database of 15 million photos her team built to "teach" a computer to understand pictures -- and the key insights yet to come.

Fei-Fei Li: How we're teaching computers to understand pictures

How we're teaching computers to understand pictures

Unlocking computer vision could revolutionize diagnostics, making cars safer and aiding disaster response with tireless accuracy.

By mirroring a child’s learning process, AI is being taught to see, bridging the gap between capturing images and understanding them.

The ImageNet project, amassing 15 million images, propels AI vision by offering unprecedented data quality and quantity for learning.