Compositionality in rational analysis: Grammar-based induction for concept learning
Name
compositionality.pdf
Description
Accepted version
Size
177.42 KB
Format
Adobe PDF
Checksum (MD5)
d6ef7f6078755bd49bb68f1827e6bf2b
Author(s)
Goodman, Noah D.
Tenenbaum, Joshua B.
Griffiths, Thomas L.
Feldman, Jacob
Date Issued
2008
Journal
The Probabilistic Mind: Prospects for Bayesian Cognitive Science
Publisher
Oxford University Press
Citation
Goodman, Noah D. et al. "Compositionality in rational analysis: Grammar-based induction for concept learning."
The Probabilistic Mind: Prospects for Bayesian Cognitive Science, edited by Nick Chater and Mike Oaksford, Oxford University Press, 2008. © 2008 Oxford University Press
Version
Author's final manuscript
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. Keywords: probabilistic research; knowledge; grammar; concept learning; cognitive science; artificial intelligence
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1093/acprof:oso/9780199216093.003.0017
