摘要
自组织竞争神经网络通过对网络输入权值的调整,使所有权矢量都在输入矢量空间相互分离,形成了各自代表输入空间的一类模式,从而实现聚类功能。应用MATLAB工具箱提供的函数,可以用自组织神经网络进行聚类分析和仿真。
Self-organizing competitive neutral net can make the weights separate mutually through the adjustment of the input weights, and the weights can represent different models in different space. So the input can be clustered by the self-organizing competitive neutral net. We can do clustering and simulating with the self-organizing competitive neutral net by using MATLAB toolboxes.
出处
《邢台职业技术学院学报》
2005年第1期45-47,共3页
Journal of Xingtai Polytechnic College
关键词
聚类分析
自组织竞争神经网络
竞争层
仿真
cluster
self-organizing competitive neutral net
competitive layer
stimulate
