Even deeper problems with neural network models of language.

Journal: The Behavioral and brain sciences
Published Date: Dec 6, 2023

Abstract

We recognize today's deep neural network (DNN) models of language behaviors as engineering achievements. However, what we know intuitively and scientifically about language shows that what DNNs are and how they are trained on bare texts, makes them poor models of mind and brain for language organization, as it interacts with infant biology, maturation, experience, unique principles, and natural law.

Authors

  • Thomas G Bever
    Department of Linguistics, University of Arizona, Tucson, AZ, USA tgb@arizona.edu nchomsky3@gmail.com Sandiway@arizona.edu Massimo@arizona.eduhttps://bever.infohttps://chomsky.infohttps://sandiway.arizona.eduhttps://massimo.sbs.arizona.edu.
  • Noam Chomsky
    Department of Linguistics, University of Arizona, Tucson, AZ, USA tgb@arizona.edu nchomsky3@gmail.com Sandiway@arizona.edu Massimo@arizona.eduhttps://bever.infohttps://chomsky.infohttps://sandiway.arizona.eduhttps://massimo.sbs.arizona.edu.
  • Sandiway Fong
    Department of Linguistics, University of Arizona, Tucson, AZ, USA tgb@arizona.edu nchomsky3@gmail.com Sandiway@arizona.edu Massimo@arizona.eduhttps://bever.infohttps://chomsky.infohttps://sandiway.arizona.eduhttps://massimo.sbs.arizona.edu.
  • Massimo Piattelli-Palmarini
    Department of Linguistics, University of Arizona, Tucson, AZ, USA tgb@arizona.edu nchomsky3@gmail.com Sandiway@arizona.edu Massimo@arizona.eduhttps://bever.infohttps://chomsky.infohttps://sandiway.arizona.eduhttps://massimo.sbs.arizona.edu.

Keywords

External Resources

Popular Topics
Recent Journals