Relational learning re-examined

C. Thornton*, A. Clark

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

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 languageEnglish
Pages (from-to)83-90
Number of pages8
JournalBehavioral and Brain Sciences
Volume20
Issue number1
Publication statusPublished - 1997
Externally publishedYes

Fingerprint

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

Cite this