Neither neural networks nor the language-of-thought alone make a complete game.

Journal: The Behavioral and brain sciences
PMID:

Abstract

Cognitive science has evolved since early disputes between radical empiricism and radical nativism. The authors are reacting to the revival of radical empiricism spurred by recent successes in deep neural network (NN) models. We agree that language-like mental representations (language-of-thoughts [LoTs]) are part of the best game in town, but they cannot be understood independent of the other players.

Authors

  • Iris Oved
    Independent Scholar, 911 Central Ave; San Francisco, CA, USA irisoved@gmail.com, irisoved@paradoxlab.org.
  • Nikhil Krishnaswamy
    Department of Computer Science, Colorado State University, Fort Collins, CO, USA nikhil.krishnaswamy@colostate.edu, https://www.nikhilkrishnaswamy.com/.
  • James Pustejovsky
    Brandeis University Department of Computer Science, South St, Waltham, MA, USA.
  • Joshua K Hartshorne
    Department of Psychology and Neuroscience, Boston College, Boston, MA 02467, USA.