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

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

doi:10.1093/acprof:oso/9780199216093.003.0017

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 proceeding › Chapter

2 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 language	English (US)
Title of host publication	The Probabilistic Mind
Subtitle of host publication	Prospects for Bayesian cognitive science
Publisher	Oxford University Press
ISBN (Electronic)	9780191695971
ISBN (Print)	9780199216093
DOIs	https://doi.org/10.1093/acprof:oso/9780199216093.003.0017
State	Published - Mar 22 2012
Externally published	Yes

All Science Journal Classification (ASJC) codes

General Psychology

Keywords

Artificial intelligence
Cognitive science
Concept learning
Grammar
Knowledge
Probabilistic research

Access to Document

10.1093/acprof:oso/9780199216093.003.0017

Cite this

@inbook{232dc8793d1a44cf808641d6792f8e10,

title = "Compositionality in rational analysis: Grammar-based induction for concept learning",

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 = "Artificial intelligence, Cognitive science, Concept learning, Grammar, Knowledge, Probabilistic research",

author = "Goodman, {Noah D.} and Tenenbaum, {Joshua B.} and Griffiths, {Thomas L.} and Jacob Feldman",

year = "2012",

month = mar,

day = "22",

doi = "10.1093/acprof:oso/9780199216093.003.0017",

language = "English (US)",

isbn = "9780199216093",

booktitle = "The Probabilistic Mind",

publisher = "Oxford University Press",

address = "United Kingdom",

}

TY - CHAP

T1 - Compositionality in rational analysis

T2 - Grammar-based induction for concept learning

AU - Goodman, Noah D.

AU - Tenenbaum, Joshua B.

AU - Griffiths, Thomas L.

AU - Feldman, Jacob

PY - 2012/3/22

Y1 - 2012/3/22

N2 - 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.

AB - 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.

KW - Artificial intelligence

KW - Cognitive science

KW - Concept learning

KW - Grammar

KW - Knowledge

KW - Probabilistic research

UR - http://www.scopus.com/inward/record.url?scp=84922760428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922760428&partnerID=8YFLogxK

U2 - 10.1093/acprof:oso/9780199216093.003.0017

DO - 10.1093/acprof:oso/9780199216093.003.0017

M3 - Chapter

AN - SCOPUS:84922760428

SN - 9780199216093

BT - The Probabilistic Mind

PB - Oxford University Press

ER -

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

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this