Implications of capacity-limited, generative models for human vision.

Journal: The Behavioral and brain sciences
Published Date:

Abstract

Although discriminative deep neural networks are currently dominant in cognitive modeling, we suggest that capacity-limited, generative models are a promising avenue for future work. Generative models tend to learn both local and global features of stimuli and, when properly constrained, can learn componential representations and response biases found in people's behaviors.

Authors

  • Joseph Scott German
    Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY 14627, United States. Electronic address: jgerman6@ur.rochester.edu.
  • Robert A Jacobs
    Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY 14627, United States. Electronic address: rjacobs@ur.rochester.edu.