RULE GENERATION FROM NEURAL NETWORKS

被引：204

作者：

FU, LM

机构：

[1] University of Florida, Department of Computer and Information Sciences,301 CSE, Gainesville, FL

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1994年 / 24卷 / 08期

基金：

美国国家科学基金会;

关键词：

NEURAL NETWORK; KNOWLEDGE-BASED SYSTEM; MACHINE LEARNING; RULE-BASED SYSTEM;

D O I：

10.1109/21.299696

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The neural network approach has proven useful for the development of artificial intelligence systems. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. In this paper, we show how to interpret neural network knowledge in symbolic form. We lay down required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. The main result is a formalized relationship between a neural network and a rule-based system. In addition, it has been demonstrated that the neural network generates rules of better performance than the decision tree approach in noisy conditions.

引用

页码：1114 / 1124

页数：11