Performance Enhancement of SLFNs in Classification by Reducing Effect of Outliers
Hieu Trung Huynh, Yonggwan Won · ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications · 2007
In this paper, an approach for outlier reduction is proposed to enhance the classification performance of the single-hidden layer feed-forward neural networks (SLFNs). Outliers in the data set are detected based on the distribution on every feature, in which scores are assigned to patterns. Patterns detected as outliers based on these scores will contribute very little in estimating the weights of SLFNs. The experimental results show that, the proposed approach can obtain high accuracy with fast learning speed if there exist outliers in the training set.