TOWARD AN ART AND SCIENCE OF KNOWLEDGE ENGINEERING - A CASE FOR BELIEF NETWORKS

被引：5

作者：

ABRAMSON, B

NG, KC

机构：

[1] UNIV SO CALIF,INST SOCIAL SCI,LOS ANGELES,CA 90089

[2] UNIV SO CALIF,DEPT PATHOL,LOS ANGELES,CA 90089

来源：

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING | 1993年 / 5卷 / 04期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/69.234781

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 discusses the the knowledge engineering of belief networks. It begins by describing several design issues that arose during the construction of two belief network-based systems, Pathfinder and ARCO1. It then addresses the issues of accuracy, consistency, and calibration as they emerged during the design of these systems, and shows how the compatibility of all networks designed for the same domain suggests an architecture for combining the recommendations of independently designed knowledge bases into a single, consensus recommendation.

引用

页码：705 / 712

页数：8

共 31 条

[1] USING BELIEF NETWORKS TO FORECAST OIL PRICES [J].

ABRAMSON, B ;

FINIZZA, A .

INTERNATIONAL JOURNAL OF FORECASTING, 1991, 7 (03) :299-315

[2]

Abramson B., 1990, Journal of Experimental and Theoretical Artificial Intelligence, V2, P241, DOI 10.1080/09528139008953725

[3]

ABRAMSON B, 1991, 13TH P N AM C INT AS, P93

[4]

Blanning R. W., 1987, Decision Support Systems, V3, P343, DOI 10.1016/0167-9236(87)90105-9

[5]

Boose J. H., 1989, Knowledge Acquisition, V1, P3, DOI 10.1016/S1042-8143(89)80003-2

[6]

Buchanan B. G., 1984, MYCIN EXPT STANFORD

[7]

Chandrasekaran B., 1986, IEEE Expert, V1, P23, DOI 10.1109/MEX.1986.4306977

[8]

Cheeseman P., 1988, Computational Intelligence, V4, P58, DOI 10.1111/j.1467-8640.1988.tb00091.x

[9]

CHEESEMAN P, 1988, COMPUTATIONAL INTELL, V4, P129

[10] ROBUST BEAUTY OF IMPROPER LINEAR-MODELS IN DECISION-MAKING [J].

DAWES, RM .

AMERICAN PSYCHOLOGIST, 1979, 34 (07) :571-582

← 1 2 3 4 →