| 引用本文： |
-
周永权,谢宁新.山峰-减法聚类神经元模型及学习算法[J].广西科学院学报,2002,(4):148-150,154. [点击复制]
- Zhou Yongquan,Xie Ningxin.Clustering Neuron Model of Peak-subtraction and Learning Algorithm[J].Journal of Guangxi Academy of Sciences,2002,(4):148-150,154. [点击复制]
|
|
| 摘要: |
| 将神经网络与数据集的密度指标结合起来提出一种山峰-减法聚类神经网络方法,利用数据集的密度指标对基类进行合并,并不断重复直至产生足够多的聚类中心,就可完成对聚类神经元的学习。给出该聚类的神经元模型和学习算法。该方法的主要优点是对于工程应用中的大样本集分类和重叠数据的模式分类问题,显得非常有效。 |
| 关键词: 聚类法 激励函数 聚类神经元 学习算法 |
| DOI： |
| 投稿时间：2002-01-05 |
| 基金项目:广西自然科学基金的资助项目(桂科基0141034) |
|
| Clustering Neuron Model of Peak-subtraction and Learning Algorithm |
|
Zhou Yongquan, Xie Ningxin
|
| (Department of Mathematical and Computer Science, Guangxi University for Nationalities, Nanning, 530006) |
| Abstract: |
| A clustering neuron model with neuron activation function variable,which is peak-subtraction clustering neuron model,is proposed in the combination of neuron network and density indexes of data sets.The new model has more advantages in solving the problems of classifications of the big sample sets and overlap data modes in engineering application. |
| Key words: clustering activation function clustering neuron learning algorithm |
