Basic ELM Algorithms

MATLAB version

The MATLAB codes of basic ELM (with randomly generated hidden nodes, random neurons) are available for download now. These random hidden nodes include sigmoid, RBF, Fourier Series, etc.

Sources of ELM with kernels (for both regression and multi-class classification) are also available for download now.

Sources of OS-ELM are available for download.

 

C/C++ version

Thank Vladislavs Dovgalecs from University of Rouen, Italy, for the kind contribution of C/C++ version of ELM, which can be downloaded from this ELM web portal. A blog entry describing briefly the algorithm and its main benefits as well as a link to the code can be found at http://dovgalecs.com/blog/extreme-learning-machine-matlab-mex-implementation/

This code has not been verifitied by this ELM web portal. Researchers can refer to the contributor for any questions/insutrations.

 

Python version

Thank A. Akusok, K. Bjork, Y. Miche, and A. Lendasse for the kind contribution of Python version of ELM can be found in https://pypi.python.org/pypi/hpelm

Thank David Lambert for the kind contribution of Python version of ELM, which can be downloaded from this ELM web portal. A blog entry describing briefly the algorithm and a link to the code can be found at https://github.com/dclambert/Python-ELM

This code has not been verifitied by this ELM web portal. Researchers can refer to the contributor for any questions/insutrations.

 

JAVA version

Thank Dong Li for the kind contribution of Java version of ELM, which can be downloaded from this ELM web portal.

This code has not been verifitied by this ELM web portal. Researchers can refer to the contributor for any questions/insutrations.

 

Multi-Layer / Hierarchical ELM

Multi-layer ELM for MNIST OCR - ELM auto encoder

L. L. C. Kasun, H. Zhou, G.-B. Huang, and C. M. Vong, “Representational Learning with Extreme Learning Machine for Big Data,” IEEE Intelligent Systems,  vol. 28, no. 6, pp. 31-34, December 2013.

 

Hierarchical ELM - H-ELM

Jiexiong Tang, Chenwei Deng, and Guang-Bin Huang, “Extreme Learning Machine for Multilayer Perceptron,” (accepted by)IEEE Transactions on Neural Networks and Learning Systems, 2015.

 

Other ELM Related Source Codes

3D Graphics Shape - http://www.kevinkaixu.net/project/mvd-elm.html,

Z. Xie, K. Xu, W. Shan, L. Liu, Y. Xiong, and H. Huang, "Projective Feature Learning for 3D Shapes with Multi-View Depth Images," Pacific Graphics, vol. 24, no. 7, 2015

High-Performance Extreme Learning Machines - https://pypi.python.org/pypi/hpelm, https://github.com/akusok/hpelm

A. Akusok, K. Bjork, Y. Miche, and A. Lendasse, "High-Performance Extreme Learning Machines: A Complete Toolbox for Big Data Applications," IEEE Open Access, vol. 3, 2015

 

Protein and genome analysis - BETAWARE

C. Savojardo, P. Fariselli, and R. Casadio, “BETAWARE: a machine-learning tool to detect and predict transmembrane beta barrel proteins in Prokaryotes,” Bioinformatics, Jan 13 2013. [source-codes link: BETAWARE] (for protein and genome analysis)

 

Prediction of electronic excitation energies of BODIPY fluorescent dyes - EEEBPre

J.-N. Wang, J.-L. Jin, Y. Geng, S.-L. Sun, H.-L. Xu, Y.-H. Lu and Z.-M. Su, "An accurate and efficient method to predict the electronic excitation energies of BODIPY fluorescent dyes," Journal of Computational Chemistry, vol. 34, no. 7, pp. 566-575, 2013 [Free Online Web Service:EEEBPre -ELM based prediction of electronic excitation energies for BODIPY dyes, which is freely accessible to public at the web site: http://202.198.129.218, has been built for prediction by the authors. This web server can return the predicted electronic excitation energy values of BODIPY dyes that are high consistent with the experimental values. The authors hope that this web server would be helpful to theoretical and experimental chemists in related research.]

 

Weighted ELM for imbalanced datasets - Weighted-ELM

W. Zong, G.-B. Huang, and Y. Chen, “Weighted extreme learning machine for imbalance learning,” Neurocomputing, vol. 101, pp. 229-242, 2013.

 

Bidirectional extreme learning machine - B-ELM

Y. Yang, Y. Wang, and X. Yuan, "Bidirectional extreme learning machine for regression problem and its learning effectiveness," IEEE Transactions on Neural Networks and Learning Systems, Vol. 23, pp. 1498 - 1505, 2012

 

Evolutionary ELM - SaDE-ELM

J. Cao, Z. Lin, and G.-B. Huang, “Self-adaptive evolutionary extreme learning machine,” Neural Processing Letters, vol. 36, pp. 285-305, 2012.

 

Fully complex ELM - C-ELM

M.-B. Li, G.-B. Huang, P. Saratchandran, and N. Sundararajan, “Fully Complex Extreme Learning Machine,” Neurocomputing, vol. 68, pp. 306-314, 2005.

 

Online Sequential ELM - OS-ELM

N.-Y. Liang, G.-B. Huang, P. Saratchandran, and N. Sundararajan, “A Fast and Accurate On-line Sequential Learning Algorithm for Feedforward Networks," IEEE Transactions on Neural Networks, vol. 17, no. 6, pp. 1411-1423, 2006

 

Clustering ELM - SS-ELM / US-ELM

G. Huang, S. Song, J. N. D. Gupta, and C. Wu, “Semi-supervised and Unsupervised Extreme Learning Machines,” (in press) IEEE Transactions on Cybernetics, 2014.