How variability shapes learning and generalization
Learning is using past experiences to inform new behaviors and actions. Because all
experiences are unique, learning always requires some generalization. An effective way of …
experiences are unique, learning always requires some generalization. An effective way of …
[HTML][HTML] Symmetry-based representations for artificial and biological general intelligence
Biological intelligence is remarkable in its ability to produce complex behaviour in many
diverse situations through data efficient, generalisable and transferable skill acquisition. It is …
diverse situations through data efficient, generalisable and transferable skill acquisition. It is …
From play to language: Infants' actions on objects cascade to word learning
C Suarez‐Rivera, E Linn… - Language …, 2022 - Wiley Online Library
Infants build knowledge by acting on the world. We conducted an ecologically grounded test
of an embodied learning hypothesis: that infants' active engagement with objects in the …
of an embodied learning hypothesis: that infants' active engagement with objects in the …
Looking is not enough: Multimodal attention supports the real‐time learning of new words
SE Schroer, C Yu - Developmental Science, 2023 - Wiley Online Library
Most research on early language learning focuses on the objects that infants see and the
words they hear in their daily lives, although growing evidence suggests that motor …
words they hear in their daily lives, although growing evidence suggests that motor …
Using deep neural networks to disentangle visual and semantic information in human perception and memory
Mental representations of familiar categories are composed of visual and semantic
information. Disentangling the contributions of visual and semantic information in humans is …
information. Disentangling the contributions of visual and semantic information in humans is …
Enhancing adversarial robustness via test-time transformation ensembling
Deep learning models are prone to being fooled by imperceptible perturbations known as
adversarial attacks. In this work, we study how equipping models with Test-time …
adversarial attacks. In this work, we study how equipping models with Test-time …
The real‐time effects of parent speech on infants' multimodal attention and dyadic coordination
SE Schroer, C Yu - Infancy, 2022 - Wiley Online Library
Parental responsiveness to infant behaviors is a strong predictor of infants' language and
cognitive outcomes. The mechanisms underlying this effect, however, are relatively …
cognitive outcomes. The mechanisms underlying this effect, however, are relatively …
Using head-mounted eye tracking to examine visual and manual exploration during naturalistic toy play in children with and without autism spectrum disorder
Multimodal exploration of objects during toy play is important for a child's development and
is suggested to be abnormal in children with autism spectrum disorder (ASD) due to either …
is suggested to be abnormal in children with autism spectrum disorder (ASD) due to either …
Building human-like communicative intelligence: A grounded perspective
M Dubova - Cognitive Systems Research, 2022 - Elsevier
Abstract Modern Artificial Intelligence (AI) systems excel at diverse tasks, from image
classification to strategy games, even outperforming humans in many of these domains …
classification to strategy games, even outperforming humans in many of these domains …
Implementing mobile eye tracking in psychological research: A practical guide
Eye tracking provides direct, temporally and spatially sensitive measures of eye gaze. It can
capture visual attention patterns from infancy through adulthood. However, commonly used …
capture visual attention patterns from infancy through adulthood. However, commonly used …