摘要
人工神经网络是在现代神经生物学研究成果的基础上发展起来的一种模拟人脑信息处理机制的网络系统,它不但具有处理数值数据的一般计算能力,而且还具有处理知识的思维、学习、记忆能力。基于神经网络的数据挖掘过程由数据准备、规则提取和规则评估三个阶段组成。研究了分解型规则抽取算法,在分析了分解型算法后,利用关联法对输入输出神经元进行关联计算,按关联度排完序之后,用神经网络进行结点选择,可以大大减少神经网络的输入结点个数数据集中数据的验证,表明了方法的有效性。
Artificial neural network is a simulated brain processing net system based on modern neural biologic research. It can not only process ordinary numeric data, but also has the ability of processing knowledge, learning and memorization. Procedure of data mining based on neural networks consists of three steps ： data preparation, rule extraction and rule evaluation. This paper discusses two kinds of rule extracting algorithms, namely pedagogical and decompositional algorithms. This procedure is to simplify the structure of the network, reduce the number of input nodes. At last, this paper has proved the effectiveness of this method.
出处
《计算机仿真》
CSCD
2008年第6期99-102,共4页
Computer Simulation
关键词
神经网络
数据挖掘
规则抽取
Neural network
Data mining
Rule extracting
