September 2017
Volume 17, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   August 2017
Eccentricity Dependent Deep Neural Networks for Modeling Human Vision
Author Affiliations
  • Gemma Roig
    Center for Brains, Minds, and Machines and McGovern Institute for Brain Research at MIT, Cambridge, MA, USA
    LCSL, Istituto Italiano di Tecnologia at MIT, Cambridge, MA, USA
  • Francis Chen
    Center for Brains, Minds, and Machines and McGovern Institute for Brain Research at MIT, Cambridge, MA, USA
  • Xavier Boix
    Center for Brains, Minds, and Machines and McGovern Institute for Brain Research at MIT, Cambridge, MA, USA
    LCSL, Istituto Italiano di Tecnologia at MIT, Cambridge, MA, USA
  • Tomaso Poggio
    Center for Brains, Minds, and Machines and McGovern Institute for Brain Research at MIT, Cambridge, MA, USA
    LCSL, Istituto Italiano di Tecnologia at MIT, Cambridge, MA, USA
Journal of Vision August 2017, Vol.17, 808. doi:10.1167/17.10.808
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Gemma Roig, Francis Chen, Xavier Boix, Tomaso Poggio; Eccentricity Dependent Deep Neural Networks for Modeling Human Vision. Journal of Vision 2017;17(10):808. doi: 10.1167/17.10.808.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

We introduce a computational model of the feedforward neural processing of a single glance of the human visual system. The model is based on deep neural networks and it builds on the invariant theory, which postulates mechanisms for invariant object representation in the human brain. Our model accounts for a diverse set of psychophysical phenomena related to object recognition. This allows to unify models of different visual mechanisms. These include invariant representations of objects, the acuity dependence with eccentricity, and crowding. We evaluate our model in the task of digit recognition using MNIST dataset. The experiments demonstrate that our model predicts the accuracy of the human visual system for recognizing digits in a flash, even in the presence of clutter. Furthermore, the results suggest that the human ability of learning new visual objects from few examples lies in the capacity of the brain to compute invariant representations of such objects with respect to geometrical transformations.

Meeting abstract presented at VSS 2017

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×