Brunel University Research Archive (BURA) >
Schools >
School of Social Sciences >
School of Social Sciences Research Papers >

Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/2275

Title: Learning perceptual schemas to avoid the utility problem
Authors: Lane, PCR
Cheng, PCH
Gobet, F
Keywords: CHREST
utility problem
knowledge
machine learning
complexity
human learning
expert
novice
perceptual expertise
PRODIGY
Soar
Electric Circuits
schema
Diagrammatic Representations
algebraic Representations
chunking
perceptual schema
multiple representations
Publication Date: 1999
Publisher: Springer
Citation: Proceedings of the Nineteenth SGES International Conference on Knowledge Based Systems and Applied Artificial Intelligence, Cambridge, 1999, pp. 72-82
Abstract: This paper describes principles for representing and organising planning knowledge in a machine learning architecture. One of the difficulties with learning about tasks requiring planning is the utility problem: as more knowledge is acquired by the learner, the utilisation of that knowledge takes on a complexity which overwhelms the mechanisms of the original task. This problem does not, however, occur with human learners: on the contrary, it is usually the case that, the more knowledgeable the learner, the greater the efficiency and accuracy in locating a solution. The reason for this lies in the types of knowledge acquired by the human learner and its organisation. We describe the basic representations which underlie the superior abilities of human experts, and describe algorithms for using equivalent representations in a machine learning architecture.
URI: http://bura.brunel.ac.uk/handle/2438/2275
Appears in Collections:School of Social Sciences Research Papers
Psychology

Files in This Item:

File Description SizeFormat
CHREST-utility-paper.pdf79.69 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.

 


Library (c) Brunel University.    Powered By: DSpace
Send us your
Feedback. Last Updated: September 14, 2010.
Managed by:
Hassan Bhuiyan