Curriculum learning with infant egocentric videos

S Sheybani, H Hansaria, J Wood… - Advances in Neural …, 2024 - proceedings.neurips.cc
Infants possess a remarkable ability to rapidly learn and process visual inputs. As an infant's
mobility increases, so does the variety and dynamics of their visual inputs. Is this change in …

Self-supervised learning through the eyes of a child

E Orhan, V Gupta, BM Lake - Advances in Neural …, 2020 - proceedings.neurips.cc
Within months of birth, children develop meaningful expectations about the world around
them. How much of this early knowledge can be explained through generic learning …

[PDF][PDF] Active Viewing in Toddlers Facilitates Visual Object Learning: An Egocentric Vision Approach.

S Bambach, DJ Crandall, LB Smith, C Yu - CogSci, 2016 - vision.soic.indiana.edu
Early visual object recognition in a world full of cluttered visual information is a complicated
task at which toddlers are incredibly efficient. In their everyday lives, toddlers constantly …

[HTML][HTML] A developmental approach to machine learning?

LB Smith, LK Slone - Frontiers in psychology, 2017 - frontiersin.org
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 …

Toddler-inspired visual object learning

S Bambach, D Crandall, L Smith… - Advances in neural …, 2018 - proceedings.neurips.cc
Real-world learning systems have practical limitations on the quality and quantity of the
training datasets that they can collect and consider. How should a system go about choosing …

The developing infant creates a curriculum for statistical learning

LB Smith, S Jayaraman, E Clerkin, C Yu - Trends in cognitive sciences, 2018 - cell.com
New efforts are using head cameras and eye-trackers worn by infants to capture everyday
visual environments from the point of view of the infant learner. From this vantage point, the …

Learning high-level visual representations from a child's perspective without strong inductive biases

AE Orhan, BM Lake - Nature Machine Intelligence, 2024 - nature.com
Young children develop sophisticated internal models of the world based on their visual
experience. Can such models be learned from a child's visual experience without strong …

A computational model of early word learning from the infant's point of view

S Tsutsui, A Chandrasekaran, MA Reza… - arXiv preprint arXiv …, 2020 - arxiv.org
Human infants have the remarkable ability to learn the associations between object names
and visual objects from inherently ambiguous experiences. Researchers in cognitive …

From simple innate biases to complex visual concepts

S Ullman, D Harari, N Dorfman - Proceedings of the …, 2012 - National Acad Sciences
Early in development, infants learn to solve visual problems that are highly challenging for
current computational methods. We present a model that deals with two fundamental …

Infants tailor their attention to maximize learning

F Poli, G Serino, RB Mars, S Hunnius - Science advances, 2020 - science.org
Infants' remarkable learning abilities allow them to rapidly acquire many complex skills. It
has been suggested that infants achieve this learning by optimally allocating their attention …