Learning Retinal Tiling in a Model of Visual Attention

Brian Cheung, Eric Weiss, Bruno Olshausen

Feb 18, 2016 (modified: Feb 18, 2016) ICLR 2016 workshop submission readers: everyone
  • Abstract: We describe a neural network model in which the tiling of the input array is learned by performing a joint localization and classification task. After training, the optimal tiling that emerges resembles the eccentricity dependent tiling of the human retina.
  • Conflicts: berkeley.edu