神经网络集成的设计与应用  

Design and Application of Neural Network Ensemble

作　　者：陈梅兰[1] 

机构地区：[1]佛山科学技术学院,佛山528000

出　　处：《现代计算机》2008年第4期28-31,共4页Modern Computer

摘　　要：传统的神经网络一般采用个体网络,其应用效果很大程度上取决于使用者的经验,且网络的泛化能力不强。一种改进的神经网络集成方法,为传统神经网络存在的问题提供了一个简易的解决方案。由理论分析和实验结果可以得出结论,神经网络集成方法比传统的个体网络方法的效果更好。The traditional neural network generally adopts an individual network, its application result is greatly decided by the user＇s experience; and the generalization of the network isn＇t quite enough. By the integrated method of neural network, it offers a simple and easy solution to the problem in the traditional neural network. With theoretical analysis and experimental resuits, the integrated method of the neural network can be concluded to be more effective than any other traditional individual network method.

关 键 词：神经网络 神经网络集成 集成学习 泛化 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]