Emergence of a 'visual number sense' in hierarchical generative models

Ivilin Stoianov, Marco Zorzi

Research output: Contribution to journalArticlepeer-review


Numerosity estimation is phylogenetically ancient and foundational to human mathematical learning, but its computational bases remain controversial. Here we show that visual numerosity emerges as a statistical property of images in 'deep networks' that learn a hierarchical generative model of the sensory input. Emergent numerosity detectors had response profiles resembling those of monkey parietal neurons and supported numerosity estimation with the same behavioral signature shown by humans and animals.

Original languageEnglish
Pages (from-to)194-196
Number of pages3
JournalNature Neuroscience
Issue number2
Publication statusPublished - Feb 2012

ASJC Scopus subject areas

  • Neuroscience(all)


Dive into the research topics of 'Emergence of a 'visual number sense' in hierarchical generative models'. Together they form a unique fingerprint.

Cite this