DocumentCode
2956674
Title
Enhanced Extreme Learning Machine with stacked generalization
Author
Zhao, Guopeng ; Shen, Zhiqi ; Miao, Chunyan ; Gay, Robert
Author_Institution
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
fYear
2008
fDate
1-8 June 2008
Firstpage
1191
Lastpage
1198
Abstract
This paper first reviews extreme learning machine (ELM) in light of coverpsilas theorem and interpolation for a comparative study with radial-basis function (RBF) networks. To improve generalization performance, a novel method of combining a set of single ELM networks using stacked generalization is proposed. Comparisons and experiment results show that the proposed stacking ELM outperforms a single ELM network for both regression and classification problems.
Keywords
learning (artificial intelligence); radial basis function networks; cover theorem; extreme learning machine; radial-basis function networks; stacked generalization; Computer errors; Feedforward neural networks; Interpolation; Iterative algorithms; Joining processes; Machine learning; Multi-layer neural network; Neural networks; Neurons; Stacking;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location
Hong Kong
ISSN
1098-7576
Print_ISBN
978-1-4244-1820-6
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2008.4633951
Filename
4633951
Link To Document