Visual learning depends on both the algorithms and the training material. This essay considers the natural statistics of infant- and toddler-egocentric vision. These natural training sets for human visual object recognition are very different from the training data fed into machine vision systems. Rather than equal experiences with all kinds of things, toddlers experience extremely skewed distributions with many repeated occurrences of a very few things. And though highly variable when considered as a whole, individual views of things are experienced in a specific order – with slow, smooth visual changes moment-to-moment, and developmentally ordered transitions in scene content. We propose that the skewed, ordered, biased visual experiences of infants and toddlers are the training data that allow human learners to develop a way to recognize everything, both the pervasively present entities and the rarely encountered ones. The joint consideration of real-world statistics for learning by researchers of human and machine learning seems likely to bring advances in both disciplines.

Much research has documented infants' sensitivity to statistical regularities in auditory and visual inputs, however the manner in which infants process and represent statistically defined information remains unclear. Two types of models have been proposed to account for this sensitivity: statistical models, which posit that learners represent statistical relations between elements in the input; and chunking models, which posit that learners represent statistically-coherent units of information from the input. Here, we evaluated the fit of these two types of models to behavioral data that we obtained from 8-month-old infants across four visual sequence-learning experiments. Experiments examined infants' representations of two types of structures about which statistical and chunking models make contrasting predictions: illusory sequences (Experiment 1) and embedded sequences (Experiments 2-4). In all four experiments, infants discriminated between high probability sequences and low probability part-sequences, providing strong evidence of learning. Critically, infants also discriminated between high probability sequences and statistically-matched sequences (illusory sequences in Experiment 1, embedded sequences in Experiments 2-3), suggesting that infants learned coherent chunks of elements. Experiment 4 examined the temporal nature of chunking, and demonstrated that the fate of embedded chunks depends on amount of exposure. These studies contribute important new data on infants' visual statistical learning ability, and suggest that the representations that result from infants' visual statistical learning are best captured by chunking models.

Object names are a major component of early vocabularies and learning object names depends on being able to visually recognize objects in the world. However, the fundamental visual challenge of the moment-to-moment variations in object appearances that learners must resolve has received little attention in word learning research. Here we provide the first evidence that image-level object variability matters and may be the link that connects infant object manipulation to vocabulary development. Using head-mounted eye tracking, the present study objectively measured individual differences in the moment-to-moment variability of visual in-

How do infants learn to mentally rotate objects, to imagine them rotating through different viewpoints? One possibility is that development of infants’ mental rotation (MR) is facilitated by visual and manual experience with complex objects. To evaluate this possibility, eighty 4-month-olds (40 females, 40 males) participated in an object exploration task with Velcro “sticky mittens” that allow infants too young to grasp objects themselves to nonetheless explore those objects manually as well as visually. These eighty infants also participated in a visual habituation task designed to test MR. Half the infants (Mittens First group) explored the object prior to the MR task, and the other half afterwards (Mittens Second group), to examine the role of immediate prior object experience on MR performance. We compared performance of male and female infants, but found little evidence for sex differences. However, we found an important effect of object exploration: The infants in the Mittens First group who exhibited the highest levels of spontaneous object engagement showed the strongest evidence of MR, but there were no consistent correlations between these measures for infants in the Mittens Second group. These findings suggest an important contribution from object experience to development of MR.

Past research suggests infants have powerful statistical learning abilities; however, studies of infants’ visual statistical learning offer differing accounts of the developmental trajectory of and constraints on this learning. To elucidate this issue, the present study tested the hypothesis that young infants’ segmentation of visual sequences depends upon redundant statistical cues to segmentation. Twenty 2-month-olds and twenty 5-month-olds observed a continuous sequence of looming shapes in which unit boundaries were defined by both transitional probability and co-occurrence frequency. Following habituation, only 5-month-olds showed evidence of statistically segmenting the sequence, looking longer to a statistically improbable shape pair than to a probable pair. These results reaffirm the power of statistical learning in infants as young as 5 months, but also suggest considerable development of statistical segmentation ability between 2 and 5 months of age. Moreover, the results do not support the idea that infants’ ability to segment visual sequences based on transitional probabilities and/or co-occurrence frequencies is functional at the onset of visual experience, as has been previously suggested. Rather, this type of statistical segmentation appears to be constrained by the developmental state of the learner. Factors contributing to the development of statistical segmentation ability in early infancy, including memory and attention, are discussed.