INTERPRETATION OF NEURAL NETWORKS AS BOOLEAN TRANSFER-FUNCTIONS

被引：4
|
作者：
FLETCHER, GP
HINDE, CJ
机构：
[1] Department of Computer Studies, University of Technology, Loughborough
来源：
KNOWLEDGE-BASED SYSTEMS | 1994年 / 7卷 / 03期
关键词：
NEURAL NETWORKS; RULE EXTRACTION; RULE INDUCTION;
D O I：
10.1016/0950-7051(94)90007-8
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
An algorithm for converting neural networks into Boolean functions is presented. The absence of such an algorithm has been identified in the literature as a significant problem, and the solution shown in the paper is both complete and efficient. The analysis of the algorithm shows it to have a time complexity of better than 2N-1 - 2(N/2)-1 + 1.
引用
收藏
页码：207 / 214
页数：8
相关论文
共 50 条
12345