Selecting Features with Neural Networks

摘要：

We present a neural network based approach for identifying salient features for classification in feedforward neural networks. Our approach involves neural network training with an augmented crossentropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the crossvalidation data set classification error due to the removal of the individual features. We compared the approach with five other feature selection methods, each of which banks on different concept. The algorithm developed outperformed the other methods by achieving a higher classification accuracy on all the problems tested.

作者: A. Verikas M. Bacauskiene K.Malmqvist

作者单位: lntelligent Systems Laboratory, Halmstad University, S 301 18 Halmstad, Sweden;Department of Applied Department of Applied Electronics, Kaunas University of Technology, LT-3031, Kaunas, Lithuania lntelligent Systems Laboratory, Halmstad University, S 301 18 Halmstad, Sweden

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 101-106

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）