Small neural networks simulate infant sensory experiences by age
Simulating Infant Senses with Age-Tuned Networks
Machine LearningHuman-Computer Interaction
Summary
Understanding how babies see, hear, and feel as they grow is complicated because each sense develops differently. The authors combined measurements of infants’ senses from birth to age two into simple computer models that simulate how babies perceive the world at different ages. These models show that even without extra instructions, things like critical periods in vision happen naturally. The authors also created an interactive website where users can see and hear the world as a baby might.
What this means in practice
- •For educational technology developers: Develop interactive tools that simulate how infants perceive images and sounds at different ages for early childhood education.
- •For virtual reality designers: Create age-specific sensory experiences in VR that mimic infant perception using age-tuned neural networks.$Commercial implications: Allows commercial VR products to deliver realistic infant sensory simulations for training or entertainment.
Authors
Somesh Mohapatra
Abstract
What a newborn sees, hears and feels, and how this changes month by month, has been measured sense by sense, with different methods and in different units. We bring these measurements together for the first two years of life and ask whether small neural networks tuned to a given age can turn them into a quick, inspectable simulation of sensory perception. Each sense's immaturity is written as a fixed, age-indexed filter on the input, and a small prediction network learns behind it over the first year. The filters alone reproduce the order in which the senses mature, by construction. The networks add what filters cannot: in vision they extract far less than their input allows at early stages (at the newborn stage a toy's position cannot be read out, $R^2 = 0.00$, against 0.57 for a network trained directly on the same input), and a critical period and perceptual narrowing emerge without being built in; in hearing they track what their input allows. The same filters drive the Baby Senses Lab, a free website that shows a user's own images and sounds as a baby of a chosen age might sense them. It is a research and teaching tool, not a diagnostic test.