SUSTAIN

A Network Model of Category Learning

Bradley C. Love, Douglas L. Medin, Todd Gureckis

Research output: Contribution to journalArticle

Abstract

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

Original languageEnglish (US)
Pages (from-to)309-332
Number of pages24
JournalPsychological Review
Volume111
Issue number2
DOIs
StatePublished - Apr 2004

Fingerprint

Learning
Birds
Mammals

ASJC Scopus subject areas

  • Psychology(all)

Cite this

SUSTAIN : A Network Model of Category Learning. / Love, Bradley C.; Medin, Douglas L.; Gureckis, Todd.

In: Psychological Review, Vol. 111, No. 2, 04.2004, p. 309-332.

Research output: Contribution to journalArticle

Love, BC, Medin, DL & Gureckis, T 2004, 'SUSTAIN: A Network Model of Category Learning', Psychological Review, vol. 111, no. 2, pp. 309-332. https://doi.org/10.1037/0033-295X.111.2.309
Love, Bradley C. ; Medin, Douglas L. ; Gureckis, Todd. / SUSTAIN : A Network Model of Category Learning. In: Psychological Review. 2004 ; Vol. 111, No. 2. pp. 309-332.
@article{57ccca7e78274b16935b3cdc57573c7c,
title = "SUSTAIN: A Network Model of Category Learning",
abstract = "SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.",
author = "Love, {Bradley C.} and Medin, {Douglas L.} and Todd Gureckis",
year = "2004",
month = "4",
doi = "10.1037/0033-295X.111.2.309",
language = "English (US)",
volume = "111",
pages = "309--332",
journal = "Psychological Review",
issn = "0033-295X",
publisher = "American Psychological Association Inc.",
number = "2",

}

TY - JOUR

T1 - SUSTAIN

T2 - A Network Model of Category Learning

AU - Love, Bradley C.

AU - Medin, Douglas L.

AU - Gureckis, Todd

PY - 2004/4

Y1 - 2004/4

N2 - SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

AB - SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

UR - http://www.scopus.com/inward/record.url?scp=1942539715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1942539715&partnerID=8YFLogxK

U2 - 10.1037/0033-295X.111.2.309

DO - 10.1037/0033-295X.111.2.309

M3 - Article

VL - 111

SP - 309

EP - 332

JO - Psychological Review

JF - Psychological Review

SN - 0033-295X

IS - 2

ER -