中国科学院机构知识库网格系统: A new early stopping algorithm for improving neural network generalization (EI CONFERENCE)

中国科学院机构知识库网格

Chinese Academy of Sciences Institutional Repositories Grid

A new early stopping algorithm for improving neural network generalization (EI CONFERENCE)

文献类型：会议论文


作者	Liu J.-G.; Wu X.-X.
出版日期	2009
会议名称	2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009, October 10, 2009 - October 11, 2009
会议地点	Changsha, Hunan, China
关键词	As generalization ability of neural network was restricted by overfitting problem in the network's training. Early stopping algorithm based on fuzzy clustering was put forward to solve this problem in this paper. Subtractive clustering and Fuzzy C-Means clustering (FCM) were combined to realize optimal division of training set validation set and test set. How to realize this algorithm in backpropagation (BP) network by utilizing neural network toolbox and fuzzy logic toolbox in MATLAB was dwelled on. Early stopping algorithm based on fuzzy clustering and other early stopping algorithms were applied in function approximation and pattern recognition problems in validation experiments. Experiments results indicate that early stopping algorithm based on fuzzy clustering has higher precision in comparison to other early stopping algorithms. Outputs of training set validation set and test set are more accordant. 2009 IEEE.
页码	15-18
收录类别	EI
源URL	[http://ir.ciomp.ac.cn/handle/181722/33038]
专题	长春光学精密机械与物理研究所_中科院长春光机所知识产出_会议论文
推荐引用方式 GB/T 7714	Liu J.-G.,Wu X.-X.. A new early stopping algorithm for improving neural network generalization (EI CONFERENCE)[C]. 见:2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009, October 10, 2009 - October 11, 2009. Changsha, Hunan, China.

入库方式： OAI收割

来源：长春光学精密机械与物理研究所

浏览0

下载0

收藏0

其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。