A team of Indiana University researches has received a $700,000 grant to work on developing machines that "think" like toddlers. The funding from the National Science Foundation will support a study using eye-tracking technology to gather first-person image data from infants and toddlers.
Once the data is collected, it will go to a team of researchers at Georgia Tech, which will use the images to design machines that mimic toddlers’ ability to recognize objects.
Psychological and Brain Sciences Professor Linda Smith says the study will help researchers "better understand the visual side of object name learning." In a release from IU, she says, "Emerging evidence from labs across the country suggests that children who are slow word learners also are slower, or weaker, in their visual object recognition skills. It could be that learning object names teaches visual object recognition or that poor or slowly developing visual object recognition limits early word learning."
The team is looking to recruit more than 100 families to gather the data through lightweight, head-mounted mini-cameras. The children will wear the cameras for six hours in a day or multiple times over a week. Researchers are looking to gather 500 hours of video.