神经网络的泛化理论和泛化方法  

GENERALIZATION THEORY AND GENERALIZATION METHODS FOR NEURAL NETWORKS

作　　者：魏海坤[1] 徐嗣鑫[1] 宋文忠[1] 

机构地区：[1]东南大学自动化研究所,南京210096

出　　处：《自动化学报》2001年第6期806-815,共10页Acta Automatica Sinica

摘　　要：泛化能力是多层前向网最重要的性能 ,泛化问题已成为目前神经网络领域的研究热点 .文中综述了神经网络泛化理论和泛化方法的研究成果 .对泛化理论 ,重点讲述神经网络的结构复杂性和样本复杂性对泛化能力的影响 ;对泛化方法 ,则在介绍每种泛化方法的同时 ,尽量指出该方法与相应泛化理论的内在联系 .Generalization ability is the most important performance of a feed-forward neural network, and the problem of generalization is widely studied recently among the neural network community. Research on this subject can be divided into two fields: generalization theory discusses the factors that affect the generalization ability, while generalization methods try to find algorithms for improved performance. This survey reviewed the main results on generalization research, and tried to point out the relationship between generalization theory and corresponding generalization methods. A prospect on generalization research was also given.

关 键 词：神经网络 泛化能力 泛化理论 泛化方法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]