Relational learning re-examined

C. Thornton; A. Clark

Relational learning re-examined

C. Thornton^*, A. Clark

^*Corresponding author for this work

Research output: Contribution to journal › Review article

Abstract

We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call 'type-2 regularity'. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pusued includig simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'.

Original language	English
Pages (from-to)	83-90
Number of pages	8
Journal	Behavioral and Brain Sciences
Volume	20
Issue number	1
Publication status	Published - 1997
Externally published	Yes

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Relational learning re-examined'. Together they form a unique fingerprint.

Cite this

Thornton, C., & Clark, A. (1997). Relational learning re-examined. Behavioral and Brain Sciences, 20(1), 83-90.

@article{6d353aec30e14884bed7e60dd7cb77fa,

title = "Relational learning re-examined",

abstract = "We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call 'type-2 regularity'. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pusued includig simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'.",

author = "C. Thornton and A. Clark",

year = "1997",

language = "English",

volume = "20",

pages = "83--90",

journal = "The Behavioral and brain sciences",

issn = "0140-525X",

publisher = "Cambridge University Press",

number = "1",

}

TY - JOUR

T1 - Relational learning re-examined

AU - Thornton, C.

AU - Clark, A.

PY - 1997

Y1 - 1997

N2 - We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call 'type-2 regularity'. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pusued includig simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'.

AB - We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call 'type-2 regularity'. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pusued includig simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'.

UR - http://www.scopus.com/inward/record.url?scp=0030853421&partnerID=8YFLogxK

M3 - Review article

VL - 20

SP - 83

EP - 90

JO - The Behavioral and brain sciences

JF - The Behavioral and brain sciences

SN - 0140-525X

IS - 1

ER -