A neural-network model for learning domain rules based on its activation function characteristics

被引：18

作者：

Fu, LM ^{[1
]}

机构：

[1] Univ Florida, Dept Comp & Informat Sci, Gainesville, FL 32611 USA

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1998年 / 9卷 / 05期

基金：

美国国家科学基金会;

关键词：

certainty factor; generalization; machine learning; neural network; rule learning; sample complexity; VC-dimension;

D O I：

10.1109/72.712152

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A challenging problem in machine learning is to discover the domain rules from a limited number of instances, In a large complex: domain, it is often the case that the rules learned by the computer are at most approximate. To address this problem, this paper describes the CFNet which bases its activation function on the certainty factor (CF) model of expert systems, a new analysis on the computational complexity of rule learning in general is provided. A further analysis shows how this complexity can be reduced to a point where the domain rules can be accurately learned by capitalizing on the activation function characteristics of the CFNet. The claimed capability is adequately supported by empirical evaluations and comparisons with related systems.

引用

页码：787 / 795

页数：9

共 17 条

[1] Survey and critique of techniques for extracting rules from trained artificial neural networks [J].

Andrews, R ;

Diederich, J ;

Tickle, AB .

KNOWLEDGE-BASED SYSTEMS, 1995, 8 (06) :373-389

[2] What Size Net Gives Valid Generalization? [J].

Baum, Eric B. ;

Haussler, David .

NEURAL COMPUTATION, 1989, 1 (01) :151-160

[3] LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION [J].

BLUMER, A ;

EHRENFEUCHT, A ;

HAUSSLER, D ;

WARMUTH, MK .

JOURNAL OF THE ACM, 1989, 36 (04) :929-965

[4]

BUCHNAN BG, 1984, RULE BASED EXPERT SY

[5]

Fu L, 1994, NEURAL NETWORKS COMP

[6] Learning in certainty-factor-based multilayer neural networks for classification [J].

Fu, LM .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (01) :151-158

[7] KNOWLEDGE-BASED CONNECTIONISM FOR REVISING DOMAIN THEORIES [J].

FU, LM .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1993, 23 (01) :173-182

[8] RULE GENERATION FROM NEURAL NETWORKS [J].

FU, LM .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1994, 24 (08) :1114-1124

[9] QUANTIFYING INDUCTIVE BIAS - AI LEARNING ALGORITHMS AND VALIANTS LEARNING FRAMEWORK [J].

HAUSSLER, D .

ARTIFICIAL INTELLIGENCE, 1988, 36 (02) :177-221

[10]

Mitchell TM., 1997, MACH LEARN, V1

← 1 2 →