A New Early Stopping Algorithm for Improving Neural Network Generalization

摘要：

As generalization ability of neural network was restricted by overfitting problem in the networks 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.

关键词： Fuzzy Clustering Neural Network Early Stopping Overfitting

作者: Xing-xing WU Jin-guo LIU

作者单位: Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences Changchun, Jilin 130033,China

会议类型: 国际会议

会议名称: 2009 Second International Conference on Intelligent Computation Technology and Automation(2009 第二届IEEE智能计算与自动化国际会议 ICICTA 2009)

会议地点: 长沙

会议语种:英文

页码: 15-18

在线出版日期: 2009-10-10（万方平台首次上网日期，不代表论文的发表时间）