Discovering containment: from infants to machines

TL;DR

This paper explores how infants learn complex spatial concepts like containment without guidance, contrasting it with supervised machine learning, and investigates the factors influencing the order of concept acquisition.

Contribution

It introduces a new perspective on unsupervised concept learning in infants and proposes models to explain the developmental trajectory of spatial relation understanding.

Findings

Infants learn containment concepts as early as 2.5 months.

Unsupervised learning mechanisms may underlie early spatial concept acquisition.

Developmental trajectories are influenced by innate biases and environmental interactions.

Abstract

Current artificial learning systems can recognize thousands of visual categories, or play Go at a champion"s level, but cannot explain infants learning, in particular the ability to learn complex concepts without guidance, in a specific order. A notable example is the category of 'containers' and the notion of containment, one of the earliest spatial relations to be learned, starting already at 2.5 months, and preceding other common relations (e.g., support). Such spontaneous unsupervised learning stands in contrast with current highly successful computational models, which learn in a supervised manner, that is, by using large data sets of labeled examples. How can meaningful concepts be learned without guidance, and what determines the trajectory of infant learning, making some notions appear consistently earlier than others?