Investigation on AQ11, ID3 and the principle of discernibility matrix

被引：71

作者：

Wang, J ^{[1
]}

Cui, J ^{[1
]}

Zhao, K ^{[1
]}

机构：

[1] Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China

来源：

JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY | 2001年 / 16卷 / 01期

关键词：

rough set theory; principle of discernibility matrix; inductive machine learning;

D O I：

10.1007/BF02948848

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The principle of discernibility matrix serves as a tool to discuss and analyze two algorithms of traditional inductive machine learning, AQ11 and ID3. The results are: (1) AQ11 and its family can be completely specified by the principle of discernibility matrix; (2) ID3 can be partly, but not naturally, specified by the principle of discernibility matrix; and (3) The principle of discernibility matrix is employed to analyze Cendrowska sample set, and it shows the weaknesses of knowledge representation style of decision tree in theory.

引用

页码：1 / 12

页数：12

共 11 条

[1]

[Anonymous], ROUGH SET THEORETICA

[2]

CENDROWSKA J, 1988, KNOWLEDGE BASED SYST, V1, P255

[3]

GUO M, 1998, PATTERN RECOGN, V11, P292

[4]

HONG J, 1997, THEORY APPL

[5]

Hunt E. B., 1966, EXPT INDUCTION

[6]

LU RJ, 1996, ARTIFICIAL INTELLIGE

[7]

Michalski R. S., 1980, International Journal of Policy Analysis and Information Systems, V4, P125

[8]

POLKOWSKI L, 1998, ROUGH SETS KNOWLEDGE, V1, P1

[9]

Quinlan J. R., 1986, Machine Learning, V1, P81, DOI 10.1023/A:1022643204877

[10]

SKOWRON A, 1991, INTELLIGENT DECISION, P331

← 1 2 →