Article

Counting Training Creates Number-Biased Representations in Deep Neural Networks

2026-02-03

Abstract excerpt

<p>Human adults show a number bias in magnitude perception, weighting numerical information more heavily than continuous magnitudes like area. However, developmental research suggests this bias is not innate: young children show an area bias that reverses to a number bias only later in development. What drives this shift? Here, we use deep neural networks to test whether learning to count is sufficient to create n...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 46612104-7b7a-54a9-a919-e23805f2c4dc
DOI: 10.31234/osf.io/356xd_v2

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Counting Training Creates Number-Biased Representations in Deep Neural NetworksDOI 10.31234/osf.io/356xd_v2Read

Counting Training Creates Number-Biased Representations in Deep Neural NetworksSemantic proximity Read

Encoding of numerosity with robustness to object and scene identity in biologically inspired object recognition networksSemantic proximity Read

A Theory of Perceptual Number EncodingSemantic proximity Read

Enumeration module for human visual system: a recurrent on-center off-surround neural network approachSemantic proximity Read

Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity Read

The role of capacity constraints in Convolutional Neural Networks for learning random versus natural dataSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

Comparative judgements and higher cognitive processes in human numerosity estimationSemantic proximity Read

Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural NetworksSemantic proximity Read

Feature blindness: a challenge for understanding and modelling visual object recognitionSemantic proximity Read

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksSemantic proximity Read

Deep Problems with Neural Network Models of Human VisionSemantic proximity Read