Séminaire ayant lieu dans le cadre du Doctorat en informatique cognitive, en collaboration avec le centre de recherche CRIA              

TITRE : Secret in the training data: How infant behavior solves learning problems

Linda B. SMITH

Jeudi le 12 novembre 2026 à 10h30

Local PK-5115 (Il est possible d'y assister en virtuel en vous inscrivant ici)                 

RÉSUMÉ

Much of the information in the world is latent: it is not revealed without action by the perceiver. This creates direct, real-time relations between sensory input and behavior, between the current and next states of the learning system, and between inputs and the outcomes of actions on the world. I will present findings from our analyses of the visual statistics of infants’ egocentric images, collected at the scale of daily life in the home. These findings suggest that the quality and spatiotemporal structure of infants’ self-generated input contribute to their efficient learning about visual objects. When human learning is more efficient than current learning mechanisms can explain, theorists often posit intrinsic “inductive biases” that constrain learning outcomes, enabling faster and more reliable learning from complex, variable, and noisy training data. The visual statistics generated by infants and toddlers interacting with their everyday world reveal another source of constraint: the learner’s own behavior structures and biases the training data itself, rather than merely constraining the inferences drawn from it. These findings may suggest principles for designing training data that support efficient learning even in machines whose learning mechanisms differ from those of humans.

BIOGRAPHIE

Linda B. SMITH is Distinguished Professor of Psychological and Brain Sciences at Indiana University – Bloomington, IN.Taking a complex systems perspective, she seeks to understand the interdependencies among perceptual, motor and cognitive developments during the first three years of post-natal life.,  She uses wearable sensors to study how the young learner’s own behavior creates the statistical structure of the learning environments  at the scale of everyday life AI.

RÉFÉRENCES 

Ramirez, F. M., Clerkin, E. M., Crandall, D. J., & Smith, L. B. (2026). A solution to generalized learning from small training sets found in infants’ repeated visual experiences of individual objects. Proceedings of the National Academy of Sciences, 123(33), e2536143123. https://arxiv.org/pdf/2510.15060

Petroff, Z. J., Jayaraman, S., Smith, L. B., Candy, T. R., & Bonnen, K. (2025). The world through infant eyes: Evidence for the early emergence of the cardinal orientation bias. PNAS, 122(16), Article e2421277122. https://doi.org/10.1073/pnas.2421277122.  

Sheybani, S., Hansaria, H., Wood, J. N., Smith, L. B., & Tiganj, Z. (2023). Curriculum Learning with Infant Egocentric Videos. Paper to be presented at NeurIPS 2023. 

Karmazyn-Raz, H. & Smith, L.B. (2023) Sampling statistics are like story creation: A network analysis of parent-toddler exploratory play. Philosophical Transactions of the Royal Society B 

Smith, L. B., Jayaraman, S., Clerkin, E. & Yu, C. (2018). The Developing Infant Creates a Curriculum for Statistical Learning.Trends in Cognitive Sciences, 4, 325-336. PMID: 29519675 PMCID: PMC5866780