Data mining in learning classifier systems: Comparing XCS with GAssist

被引：26

作者：

Bacardit, Jaume ^{[1
]}

Butz, Martin V. ^{[2
]}

机构：

[1] Univ Nottingham, Sch Comp Sci, ASAP, Jubilee Campus, Wollaton Road, Nottingham NG8 1BB, England

[2] Univ Wurzburg, Dept Cognit Psychol, D-97070 Wurzburg, Germany

来源：

LEARNING CLASSIFIER SYSTEMS | 2007年 / 4399卷

关键词：

D O I：

10.1007/978-3-540-71231-2_19

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper compares performance of the Pittsburgh-style system GAssist with the Michigan-style system XCS on several datamining problems. Our analysis shows that both systems are suitable for datamining but have different advantages and disadvantages. The study does not only reveal important differences between the two systems but also suggests several structural properties of the underlying datasets.

引用

页码：282 / 290

页数：9

共 12 条

[1]

[Anonymous], 2004, THESIS R LLULL U BAR

[2]

[Anonymous], 2001, Proceedings of the 4th international workshop on learning classifier systems (IWLCS-2001)

[3]

[Anonymous], FESTSCHRIFT HONOR JH

[4]

[Anonymous], GECCO 01

[5]

Bacardit J, 2004, LECT NOTES COMPUT SC, V3103, P726

[6]

BACARDIT J, 2003, P SEG C ESP MET ALG, P303

[7]

BACARDIT J, 2003, IN PRESS LNAI

[8]

Blake C.L., 1998, UCI repository of machine learning databases

[9]

Butz MV, 2003, LECT NOTES COMPUT SC, V2724, P1857

[10]

BUTZ MV, 2005, STUDIES FUZZINESS SO

← 1 2 →