摘要
聚类分析神经网络的输入样本序列具有各种不同的空间分布性态，这就要求采用不同的相似匹配准则。本文以广义距离和广义相似匹配准则为基本概念，介绍了广义聚类神经网络ＧＣ的设计思想和网络的学习训练方法，该方法具有广泛的适用性。
The input series of cluster neural networks have various characteristics in the samples′ space,which need corresponding similarity matching rules used in the networks.The design and training ideas of generalized cluster neural network GC have been introduced by using basic concepts of general distance and generalized similarity matching rule. The ideas of neural network GC are practicable in engineering.
出处
《数据采集与处理》
EI
CSCD
1999年第1期1-4,共4页
Journal of Data Acquisition and Processing
关键词
人工智能
神经网络
聚类分析
自适应系统
GC
artificial intelligence
neural networks
cluster analysis
adaptive systems
