Abstract
According to conventional neural network theories, the feature of single-hidden-layer feedforward neural networks(SLFNs) resorts to parameters of the weighted connections and hidden nodes. SLFNs are universal approximators when at least the parameters of the networks including hidden-node parameter and output weight exist. Unlike above neural network theories, this paper indicates that in order to let SLFNs work as universal approximators, one may simply calculate only the hidden node parameter and the output weight is not required at all. In other words, this proposed neural network architecture can be considered as a standard SLFN without output weights. Furthermore, this paper presents experiments which show that the proposed learning method tends to extremely reduce network output error to a very small number with only several hidden nodes. Simulation results demonstrate that the proposed method can provide hundreds times faster learning speed compared to other learning algorithms including BP, SVM/SVR and other ELM methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lin, H.T., Liang, T.J., Chen, S.M.: Estimation of battery state of health using probabilistic neural network. IEEE Transactions on Industrial Informatics 9(2), 679–685 (2013)
Zhang, R., Lan, Y., Huang, G.B., Xu, Z.B.: Universal approximation of extreme learning machine with adaptive growth of hidden nodes. IEEE Transactions on Neural Networks and Learning Systems 23(2), 365–371 (2012)
Igelnik, B., Pao, Y.H.: Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Transactions on Neural Networks 6(6), 1320–1329 (1995)
Pao, Y.H., Park, G.H., Sobajic, D.J.: Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6(2), 163–180 (1994)
Broomhead, D.S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Systems 2, 321–355 (1988)
Huang, G.B., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks 17(4), 879–892 (2006)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: Theory and applications. Neurocomputing 70, 489–501 (2006)
Huang, G.B., Zhou, H.M., Ding, X.J., Zhang, R.: Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics 42(2), 513–529 (2012)
Huang, G.B.: An insight into extreme learning machines: Random neurons, random features and kernels. Cognitive Computation (2014), doi:10.1007/s12559-014-9255-2
Baradarani, A., Wu, Q.M.J., Ahmadi, M.: An efficient illumination invariant face recognition framework via illumination enhancement and dd-dtcwt filtering. Pattern Recognition 46(1), 57–72 (2013)
Minhas, R., Mohammed, A.A., Wu, Q.M.J.: Incremental learning in human action recognition based on snippets. IEEE Transactions On Circuits and Systems For Video Technology 22(11), 1529–1541 (2012), doi:10.1109/TCSVT.2011.2177182
Huang, G.B., Kasun, L.L.C., Zhou, H., Vong, C.M.: Representational learning with extreme learning machine for big data. IEEE Intelligent Systems 28(6), 31–34 (2013)
Mohammed, A.A., Minhas, R., Wu, Q.M.J., Sid-Ahmed, M.A.: Human face recognition based on multidimensional pca and extreme learning machine. Pattern Recognition 44(10-11), 2588–2597 (2011)
Xu, Y., Dong, Z.Y., Xu, Z., Meng, K., Wong, K.P.: An intelligent dynamic security assessment framework for power systems with wind power. Ieee Transactions on Industrial Informatics 8(4), 995–1003 (2012)
Yang, Y.M., Wang, Y.N., Yuan, X.F.: Parallel chaos search based incremental extreme learning machine. Neural Processing Letters 37(3), 277–301 (2013)
Hunter, D., Yu, H., Pukish, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures-a comparative study. IEEE Transactions on Industrial Informatics 8(2), 228–240 (2012)
Hoerl, A.E., Kennard, R.W.: Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 42(1), 80–86 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Yang, Y., Wu, Q.M.J., Wang, Y., Mukherjee, D., Chen, Y. (2015). ELM Feature Mappings Learning: Single-Hidden-Layer Feedforward Network without Output Weight. In: Cao, J., Mao, K., Cambria, E., Man, Z., Toh, KA. (eds) Proceedings of ELM-2014 Volume 1. Proceedings in Adaptation, Learning and Optimization, vol 3. Springer, Cham. https://doi.org/10.1007/978-3-319-14063-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-14063-6_27
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14062-9
Online ISBN: 978-3-319-14063-6
eBook Packages: EngineeringEngineering (R0)