Relational learning re-examined

Thornton, Chris and Clark, Andy (1997) Relational learning re-examined. Behavioral and Brain Sciences, 20 (1). pp. 83-90. ISSN 0140-525X

Full text not available from this repository.

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 pursued including simple incremental learning, modular connectionism, and the developmental hypothesis of ''representational redescription''.

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Chris Thornton
Date Deposited: 06 Feb 2012 18:44
Last Modified: 27 Mar 2012 11:14
URI: http://sro.sussex.ac.uk/id/eprint/18038
📧 Request an update