Classification Using Extreme Learning Machine
Keywords:
classification, neural network, extreme learning machine, moore penroseAbstract
Extreme Learning Machine (ELM) has become popular for solving classification problem due to its fast speed. The performance of ELM often relies on random input hidden node parameters. Neural network also uses artificial intelligence by adjusting weights and minimizing the error. The learning speed of feed forward neural network is very slow. Due to two slow gradient-based learning algorithms and iterative tuning of various parameters. This paper presents a comparative study of back propagation algorithm and an extremely fast ELM technique for single layer feed forward neural network which takes random hidden nodes and determines the output weights without iterative tuning. In theory, this algorithm tends to provides better performance at extremely fast learning speed.
References
Guang-Bin Huang,Qin-Yu Zhu,Chee-KheongSiew,”Extreme learning machine: Theory and applications”Neurocomputing,Volume70, Issues 1–3, , Pages 489–501,December 2006.
Guang-Bin Huang,Hongming Zhou, Xiaojian Ding, and RuiZhangExtreme Learning Machine for Regression and Multiclass Classification,IEEE Transactions on Systems, Man and Cybernetics-Part B:Cybernetics,Vol-42,No.2,April 2012
G.-B. Huang, H.A. Babri”Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions”,IEEE Trans. Neural Networks, 9 (1) pp. 224–229(1998)
N.-Y. Liang, et al., “A Fast and Accurate On-line Sequential Learning Algorithm for feeedforwardNetworks,”IEEE Transactions on Neural Networks, vol. 17, no. 6, pp. 1411-1423, 2006.
Q.-Y. Zhu, et al., “Evolutionary Extreme Learning Machine”, Pattern Recognition, vol. 38, no. 10, pp.1759-1763, 2005.
R. Zhang, et al., “Multi-Category Classification Using Extreme Learning Machine for Microarray GeneExpression Cancer Diagnosis,” IEEE/ACM Transactions on Computational Biology and Bioinformatics (inpress), 2006.
P.L. Bartlett, The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network, IEEE Trans. Inf. Theory 44 (2) 525–536 (1998).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2013 COMPUSOFT: An International Journal of Advanced Computer Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
©2023. COMPUSOFT: AN INTERNATIONAL OF ADVANCED COMPUTER TECHNOLOGY by COMPUSOFT PUBLICATION is licensed under a Creative Commons Attribution 4.0 International License. Based on a work at COMPUSOFT: AN INTERNATIONAL OF ADVANCED COMPUTER TECHNOLOGY. Permissions beyond the scope of this license may be available at Creative Commons Attribution 4.0 International Public License.
