Letter perception emerges from unsupervised deep learning and recycling of natural image features
Letter perception emerges from unsupervised deep learning and recycling of natural image features
Alberto Testolin,Ivilin Peev Stoianov,M. Zorzi
2017 · DOI: 10.1038/s41562-017-0186-2
Nature Human Behaviour · 52 Citations
TLDR
A large-scale computational model of letter recognition based on deep learning 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.