Modeling infant visual preference as perceptual oscillation

Infants' visual recognition abilities are typically studied using variations of preferential looking paradigms. In this broad class of tasks, the extent to which infants discriminate between, categorize, and recognize complex images is determined by which of two test images they prefer to look at. This preference is usually expressed by calculating the proportion of total looking time allocated to a target stimulus (e.g., the stimulus that is more novel) on each trial. Although this coarse description of infant looking behavior has been sufficient to reveal a wide range of important effects, it also potentially obscures great deal of important visual behavior. As a result, we know less about changes in infant looking over learning and development than we would if visual behavior were measured in other ways. We argue that deeper understanding of learning and development of infants' visual behavior requires appreciation of the dynamics of that behavior: During any individual trial, infants look back and forth between stimuli several times. These oscillations between stimuli may reflect aspects of visual processing that have been heretofore overlooked. We suggest that modeling the distribution of look durations made across trials provides a rich description of looking behavior that makes it possible to approach preferential looking as a form of perceptual oscillation, and may provide additional understanding into learning and development. Here we show how fitting the parameters of a gamma distribution to infants' look durations in a face recognition task allows us to see effects that are not evident when simpler descriptors are used and discuss how this approach supports the interpretation of infant behavioral data in the context of neural models of visual competition.