The basic assumption was that people of different ages were attracted to different things. So, it is possible to determine a person’s age by eye movement.
The experiment involved 19 toddlers who were 18 months old and 22 children aged two and a half. Each child had a special device on his or her head that tracked gaze direction. The subjects were shown various objects. The toddlers paid attention to people’s faces while the 2.5-year-olds tended to look more at touchable things.
All data were carefully recorded and used for machine learning. Subsequently, the neural network learned to determine a child’s age based solely on his gaze direction trajectory. The answers were 83% accurate. This unusual computer application only highlights the fact that there is no limit to technological development and humanity has many new frontiers to strive for.