Skip to yearly menu bar Skip to main content


Poster
in
Workshop: MATH-AI: The 3rd Workshop on Mathematical Reasoning and AI

CNN models' sensitivity to numerosity concepts

Neha Upadhyay · Sashank Varma

Keywords: [ CNN ] [ numerosity ] [ Cognitive Science ] [ cognitive modeling ] [ Computer Vision ] [ number line ]


Abstract:

The nature of number is a classic question in the philosophy of mathematics. Cognitive science research shows that numbers are mentally represented as magnitudes organized as a mental number line (MNL). Here we ask whether CNN models, in learning to classify images, learn about number and numerosity 'for free'. This was the case. The models show the distance, size, and ratio effects that are the signatures of magnitude representations in humans. An MDS analysis of their latent representations found a close resemblance to the MNL documented in people. These findings challenge the developmental science proposal that numbers are part of the ‘core knowledge’ that all human infants possess.

Chat is not available.