Compositionality in rational analysis: Grammar-based induction for concept learning

Noah D. Goodman, Joshua B. Tenenbaum, Thomas L. Griffiths, Jacob Feldman

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Scopus citations

Abstract

This chapter provides a range of conceptual and technical insights into how this project can be attempted - and goes some way to suggesting that probabilistic methods need not be viewed as inevitably unable to capture the richness and complexity of world knowledge. It argues that structured representations, generated by a formal grammar, can be appropriate units over which probabilistic information can be represented and learned. This topic is likely to be one of the main challenges for probabilistic research in cognitive science and artificial intelligence over the coming decades.

Original languageEnglish (US)
Title of host publicationThe Probabilistic Mind
Subtitle of host publicationProspects for Bayesian cognitive science
PublisherOxford University Press
ISBN (Electronic)9780191695971
ISBN (Print)9780199216093
DOIs
StatePublished - Mar 22 2012
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Psychology(all)

Keywords

  • Artificial intelligence
  • Cognitive science
  • Concept learning
  • Grammar
  • Knowledge
  • Probabilistic research

Fingerprint Dive into the research topics of 'Compositionality in rational analysis: Grammar-based induction for concept learning'. Together they form a unique fingerprint.

  • Cite this

    Goodman, N. D., Tenenbaum, J. B., Griffiths, T. L., & Feldman, J. (2012). Compositionality in rational analysis: Grammar-based induction for concept learning. In The Probabilistic Mind: Prospects for Bayesian cognitive science Oxford University Press. https://doi.org/10.1093/acprof:oso/9780199216093.003.0017