Letter perception emerges from unsupervised deep learning and recycling of natural image features

Alberto Testolin, Ivilin Stoianov and Marco Zorzi ()
Additional contact information
Alberto Testolin: University of Padova
Ivilin Stoianov: Centre National de la Recherche Scientifique, Aix-Marseille Université
Marco Zorzi: University of Padova

Nature Human Behaviour, 2017, vol. 1, issue 9, 657-664

Abstract: Abstract The use of written symbols is a major achievement of human cultural evolution. However, how abstract letter representations might be learned from vision is still an unsolved problem 1,2 . Here, we present a large-scale computational model of letter recognition based on deep neural networks 3,4 , which develops a hierarchy of increasingly more complex internal representations in a completely unsupervised way by fitting a probabilistic, generative model to the visual input 5,6 . In line with the hypothesis that learning written symbols partially recycles pre-existing neuronal circuits for object recognition 7 , earlier processing levels in the model exploit domain-general visual features learned from natural images, while domain-specific features emerge in upstream neurons following exposure to printed letters. We show that these high-level representations can be easily mapped to letter identities even for noise-degraded images, producing accurate simulations of a broad range of empirical findings on letter perception in human observers. Our model shows that by reusing natural visual primitives, learning written symbols only requires limited, domain-specific tuning, supporting the hypothesis that their shape has been culturally selected to match the statistical structure of natural environments 8 .

Date: 2017
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.nature.com/articles/s41562-017-0186-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nathum:v:1:y:2017:i:9:d:10.1038_s41562-017-0186-2

Ordering information: This journal article can be ordered from
https://www.nature.com/nathumbehav/

DOI: 10.1038/s41562-017-0186-2

Access Statistics for this article

Nature Human Behaviour is currently edited by Stavroula Kousta

More articles in Nature Human Behaviour from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().