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

@article{Testolin2017LetterPE,
  title={Letter perception emerges from unsupervised deep learning and recycling of natural image features},
  author={A. Testolin and I. Stoianov and M. Zorzi},
  journal={Nature Human Behaviour},
  year={2017},
  volume={1},
  pages={657-664}
}
  • A. Testolin, I. Stoianov, M. Zorzi
  • Published 2017
  • Medicine, Psychology
  • Nature Human Behaviour
  • 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 problem1,2. Here, we present a large-scale computational model of letter recognition based on deep neural networks3,4, which develops a hierarchy of increasingly more complex internal representations in a completely unsupervised way by fitting a probabilistic, generative model to the visual input5,6. In line with the… CONTINUE READING
    Deep learning systems as complex networks
    4
    The Challenge of Modeling the Acquisition of Mathematical Concepts
    3
    Perception of visual numerosity in humans and machines
    2
    Deep learning: Using machine learning to study biological vision
    4

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 91 REFERENCES