一种用于模式分类有监督的模糊ART神经网络  

A Supervised Fuzzy ART Neural Network for Pattern Classification

作　　者：潘紫微[1] 徐金梧[2] 

机构地区：[1]华东冶金学院,马鞍山243002 [2]北京科技大学机械工程学院,北京100083

出　　处：《北京科技大学学报》2000年第3期262-265,共4页Journal of University of Science and Technology Beijing

摘　　要：探讨了一种将有监督学习机制融合到模糊ART网络构成一个有监督的模糊ART神经网络模型．这种网络能同时处理有监督和无监督学习问题，并具有积累和增加网络学习的能力．对该网络进行了滚动轴承检测数据模式分类实验，并与BP网络进行了比较性实验．结果表明：该网络具有良好模式分类能力和较好的可塑性．A new neural network model that incorporates a supervised mechanism into a fuzzy ART is investigated. The model can cope with supervised learning and unsupervised learning simultaneously, and has the ability of incremental learning. A few experiments of bearing pattern classification prove pefformance of the model and by comparing pefformance of the model with BP model. The results of experiments indicate tha the model has the ability of pattem classification and flexibility.

关 键 词：模式识别 模糊ART神经网络 模式分类 有监督学习 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] O235[自动化与计算机技术—控制科学与工程]