1. Applying a new localized generalization error model to design neural networks trained with extreme learning machine
- Author
-
Jianping Yin, Victor C. M. Leung, Jun-Hai Zhai, Zhiping Cai, Jiarun Lin, and Qiang Liu
- Subjects
0209 industrial biotechnology ,Computer science ,02 engineering and technology ,Machine learning ,computer.software_genre ,020901 industrial engineering & automation ,Artificial Intelligence ,Margin (machine learning) ,0202 electrical engineering, electronic engineering, information engineering ,Extreme learning machine ,Artificial neural network ,business.industry ,Pattern recognition ,Quadratic classifier ,Generalization error ,ComputingMethodologies_PATTERNRECOGNITION ,Feature Dimension ,Principal component analysis ,Margin classifier ,Bayes error rate ,Feedforward neural network ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,Classifier (UML) ,Software - Abstract
High accuracy and low overhead are two key features of a well-designed classifier for different classification scenarios. In this paper, we propose an improved classifier using a single-hidden layer feedforward neural network (SLFN) trained with extreme learning machine. The novel classifier first utilizes principal component analysis to reduce the feature dimension and then selects the optimal architecture of the SLFN based on a new localized generalization error model in the principal component space. Experimental and statistical results on the NSL-KDD data set demonstrate that the proposed classifier can achieve a significant performance improvement compared with previous classifiers.
- Published
- 2014