摘要
本文主要研究高斯基函数分类器的训练问题，对基函数分类器来说，如何确定网络的初始隐层节点数和隐层节点参数是一个重要问题。文中采用基于遗传算法的高斯核函数聚类方法和模糊决策技术完成分类器的初始结构和参数确定，然后再采用反向传播（ＢＰ）学习算法完成分类器的最终训练，典型实验的结果表明了该方法的有效性。
This paper principally discusses the training problem of Gaussian basis function classifier which can be used for classification. For basis function classifier,how to correctly initialize the number of network hidden nodes and their parameters is very important. Genetic-based Gaussian function clustering method and fuzzy decision technique are explored to complete this work. Then by using back propagation learning algorithm,the final training can be achieved. Results from the typical experiments are used to illustrate the power and efficiency of this method.
出处
《电子学报》
EI
CAS
CSCD
北大核心
1996年第7期78-82,共5页
Acta Electronica Sinica
关键词
神经网络
分类器
高斯函数
聚类
模糊决策
Neural network, Classifier, Gaussian function, Clustering, Fuzzy decision, Back propagation
