Hostname: page-component-848d4c4894-nr4z6 Total loading time: 0 Render date: 2024-05-17T08:47:30.325Z Has data issue: false hasContentIssue false
  • English
  • Français

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

Published online by Cambridge University Press:  28 September 2023

Iris Oved ,
Nikhil Krishnaswamy Open the ORCID record for Nikhil Krishnaswamy [Opens in a new window] ,
James Pustejovsky Open the ORCID record for James Pustejovsky [Opens in a new window]  and
Joshua K. Hartshorne Open the ORCID record for Joshua K. Hartshorne [Opens in a new window]
Iris Oved
Affiliation:
Independent Scholar, 911 Central Ave; San Francisco, CA, USA irisoved@gmail.com, irisoved@paradoxlab.org
Nikhil Krishnaswamy
Affiliation:
Department of Computer Science, Colorado State University, Fort Collins, CO, USA nikhil.krishnaswamy@colostate.edu, https://www.nikhilkrishnaswamy.com/
James Pustejovsky
Affiliation:
Department of Computer Science, Brandeis University, Waltham, MA, USA jamesp@cs.brandeis.edu, https://jamespusto.com/
Joshua K. Hartshorne
Affiliation:
Department of Psychology and Neuroscience, Boston College, Chestnut Hill, MA, USA joshua.hartshorne@bc.edu, http://l3atbc.org/index.html
Get access Rights & Permissions [Opens in a new window]

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.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 46 , 2023 , e285
Check for updates
Copyright
Copyright © The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bass, I., Smith, K. A., Bonawitz, E., & Ullman, T. D. (2021). Partial mental simulation explains fallacies in physical reasoning. Cognitive Neuropsychology, 38(7–8), 413–424.CrossRefGoogle ScholarPubMed
Fodor, J. A. (1975). The language of thought (Vol. 5). Harvard University Press.Google Scholar
Goodman, N. D., Tenenbaum, J. B., & Gerstenberg, T. (2014). Concepts in a probabilistic language of thought. Center for Brains, Minds and Machines (CBMM).Google Scholar
Hartshorne, J. K., Jennings, M. V., Gerstenberg, T., & Tenenbaum, J. (2019). When circumstances change, update your pronouns. Cognitive Science (p. 3472).Google Scholar
Jackendoff, R. S. (1990). Semantic structures. MIT Press.Google Scholar
Jara-Ettinger, J., Gweon, H., Schulz, L. E., & Tenenbaum, J. B. (2016). The naïve utility calculus: Computational principles underlying commonsense psychology. Trends in Cognitive Sciences, 20(8), 589–604.CrossRefGoogle ScholarPubMed
Oved, I. (2015). Hypothesis formation and testing in the acquisition of representationally simple concepts. Philosophical Studies 172(1), 227–247.CrossRefGoogle Scholar
Pollock, J., & Oved, I. (2005). Vision, knowledge, and the mystery link. Philosophical Perspectives, 19, 309–351.CrossRefGoogle Scholar
Pustejovsky, J. (1995). The generative lexicon. MIT Press.Google Scholar
Pustejovsky, J., & Krishnaswamy, N. (2022). Multimodal semantics for affordances and actions. In Human–Computer Interaction. Theoretical Approaches and Design Methods: Thematic Area, Held as Part of the 24th HCI International Conference, Proceedings, HCII 2022, Virtual Event, June 26–July 1, 2022, Part I (pp. 137–160). Cham: Springer International Publishing.Google Scholar
Ullman, T. D., Spelke, E., Battaglia, P., & Tenenbaum, J. B. (2017). Mind games: Game engines as an architecture for intuitive physics. Trends in Cognitive Sciences, 21(9), 649–665.CrossRefGoogle ScholarPubMed
Wu, J., Yildirim, I., Lim, J. J., Freeman, B., & Tenenbaum, J. (2015). Galileo: Perceiving physical object properties by integrating a physics engine with deep learning. Advances in Neural Information Processing Systems, 28.Google Scholar