A research from Northwestern University (NU) reveals that infants can use even a few labeled examples to spark the acquisition of object categories.
Those labeled examples lead infants to initiate the process of categorization, after which they can integrate all subsequent objects, labeled or unlabeled, into their evolving category representation.
This strategy, known as "semi-supervised learning" (SSL), has been documented extensively in machine learning.
In order to test if this efficient strategy also was applicable to two-year-olds, NU researchers showed infants six objects from the same novel category, one infants had never seen before. They then varied whether and how these objects were labeled.
Infants for whom all six objects were labeled successfully learned the category, but those who heard no labels failed. Critically, infants in the semi-supervised condition, for whom only the first two objects were labeled, succeeded, learning the new category just as successfully as if all the objects were labeled.
"These results suggest that semi-supervised learning can be quite powerful," said Alexander LaTourrette, lead author of the study and a doctoral candidate in cognitive psychology in the Weinberg College of Arts and Sciences at NU.
Seeing just two labeled examples jump-starts infants' category learning. Once they've heard a few objects receive the same label, infants can learn the rest on their own, with or without labels, LaTourrette said.
The timing of the labeling also mattered. If the two labeling episodes came at the end of the learning phase, after infants had already seen the unlabeled objects, they failed to learn the category.
This shows that infants can use semi-supervised learning. They use the power of labeling to learn more from subsequent, unlabeled objects.
"This insight from machine learning sheds light on a paradox in infant development. In semi-supervised learning, labels exert a powerful influence even if they are rare," said Sandra Waxman, senior author of the study, director of the Infant and Child Development Center and faculty fellow in NU's Institute for Policy Research.
The study has been published in Developmental Science.
