摘要
竞争学习技术是神经网络用于样本分类中应用十分普通的一种方法。动态竞争学习是一种无导师学习技术，它包括产生网络的方法以及网络中新单元的产生规则，它们都是在学习中动态产生的。该模型可用于复杂数据结构的存储。
The competitive learning techniques is a well known algorithm used in neural networks which classifies the input vectors. Dynamic competitive learning is an unsuperised learning technique, which consists of two additional parts related to conventional competitive learning: a method of generation of new units within a cluster and a method of generating new clusters. The model is capable for the storage of complex data structures.
出处
《微机发展》
1997年第4期36-38,共3页
Microcomputer Development
关键词
知识表示
神经网络
竞争学习
Knowledge Representation
Neural Network
Competitive Learning
