Baby-mounted cameras teach AI to ‘see’ through a child’s eyes

By Chris Stokel-Walker

The world from a child’s perspective

Ievgen Chabanov/Alamy

The way that babies learn about and navigate the world could prove to be a good model for training artificial intelligence.

AIs don’t learn as efficiently or flexibly as children. To explore why, Brenden Lake and his colleagues at New York University turned to the SAYCam data set, which was published this year. It contains video footage from head-mounted cameras worn by young children for a few hours each week over their first three years of life.

The team fed an AI neural network raw data from SAYCam and asked …