Abstract
Extreme learning machine (ELM) is a learning algorithm for generalized single-hidden-layer feed-forward networks (SLFNs). In order to obtain a suitable network architecture, Incremental Extreme Learning Machine (I-ELM) is a sort of ELM constructing SLFNs by adding hidden nodes one by one. Although kinds of I-ELM-class algorithms were proposed to improve the convergence rate or to obtain minimal training error, they do not change the construction way of I-ELM or face the over-fitting risk. Making the testing error converge quickly and stably therefore becomes an important issue. In this paper, we proposed a new incremental ELM which is referred to as Length-Changeable Incremental Extreme Learning Machine (LCI-ELM). It allows more than one hidden node to be added to the network and the existing network will be regarded as a whole in output weights tuning. The output weights of newly added hidden nodes are determined using a partial error-minimizing method. We prove that an SLFN constructed using LCI-ELM has approximation capability on a universal compact input set as well as on a finite training set. Experimental results demonstrate that LCI-ELM achieves higher convergence rate as well as lower over-fitting risk than some competitive I-ELM-class algorithms.
Similar content being viewed by others
References
Castano A, Fernández-Navarro F, Herv´as Martinez C. PCA-ELM: A robust and pruned extreme learning machine approach based on principal component analysis. Neural Processing Letters, 2013, 37(3): 377-392.
Chen H, Gong Y, Hong X. Online modeling with tunable RBF network. IEEE Transactions on Cybernetics, 2013, 43(3): 935-947.
Frénay B, Verleysen M. Using SVMs with randomised feature spaces: An extreme learning approach. In Proc. the 18th European Symposium on Artificial Neural Networks, Apr. 2010, pp.315-320.
Shin Y, Ghosh J. Approximation of multivariate functions using ridge polynomial networks. In Proc. International Joint Conference on Neural Networks, June 1992, pp.380-385.
Park B J, KimWD, Oh S K, PedryczW. Fuzzy set-oriented neural networks based on fuzzy polynomial inference and dynamic genetic optimization. Knowledge and Information Systems, 2014, 39(1): 207-240.
[6] Han F, Huang D S. Improved extreme learning machine for function approximation by encoding a priori information. Neurocomputing, 2006, 69(16/17/18): 2369-2373.
Lin F J, Hung Y C, Ruan K C. An intelligent second-order sliding-mode control for an electric power steering system using a wavelet fuzzy neural network. IEEE Transactions on Fuzzy Systems, 2014, 22(6): 1598-1611.
Capizzi G, Capizzi C, Bonanno F. Innovative secondgeneration wavelets construction with recurrent neural networks for solar radiation forecasting. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(11): 1805-1815.
Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks, 1991, 4(2): 251-257.
Leshno M, Lin V Y, Pinkus A, Schocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, 1993, 6(6): 861-867.
Park J, Sandberg I W. Universal approximation using radial-basis-function networks. Neural Computation, 1991, 3(2): 246-257.
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications. Neurocomputing, 2006, 70(1/2/3): 489-501.
[13] Huang G B, Zhou H, Ding X, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, Cybernetics, Part B (Cybernetics), 2012, 42(2): 513-529.
Wang S J, Chen H L, Yan W J, Chen Y H, Fu X L. Face recognition and micro-expression recognition based on discriminant tensor subspace analysis plus extreme learning machine. Neural Processing Letters, 2014, 39(1): 25-43.
Liu D,Wu Y, Jiang H. FP-ELM: An online sequential learning algorithm for dealing with concept drift. Neurocomputing, 2016, 207(26): 322-334.
Han D H, Zhang X, Wang G R. Classifying uncertain and evolving data streams with distributed extreme learning machine. Journal of Computer Science and Technology, 2015, 30(4): 874-887.
Zhang T, Dai Q, Ma Z. Extreme learning machines’ ensemble selection with GRASP. Applied Intelligence, 2015, 43(2): 439-459.
Nie L, Jiang H, Ren Z et al. Query expansion based on crowd knowledge for code search. IEEE Transactions on Services Computing, 2016, 9(5): 771-783.
Deng C W, Huang G B, Xu J et al. Extreme learning machines: New trends and applications. Science China Information Sciences, 2015, 58(2): 1-16.
Jiang H, Nie L, Sun Z et al. ROSF: Leveraging information retrieval and supervised learning for recommending code snippets. IEEE Transactions on Services Computing, 2016. doi:10.1109/TSC.2016.2592909
Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892.
Wang N, Han M, Dong N, Er M J. Constructive multioutput extreme learning machine with application to large tanker motion dynamics identification. Neurocomputing, 2014, 128: 59-72.
Feng G, Huang G B, Lin Q, Gay R. Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Transactions on Neural Networks, 2009, 20(8): 1352-1357.
Wang N, Er M J, Han M. Parsimonious extreme learning machine using recursive orthogonal least squares. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(10): 1828-1841.
Miche Y, Sorjamaa A, Bas P, Simula O, Jutten C, Lendasse A. OP-ELM: Optimally pruned extreme learning machine. IEEE Transactions on Neural Networks, 2010, 21(1): 158-162.
Luo X, Liu F, Yang S, Wang X, Zhou Z. Joint sparse regularization based sparse semi-supervised extreme learning machine (S3ELM) for classification. Knowledge-Based Systems, 2015, 73: 149-160.
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, 2012, 23(2): 365-371.
Zhang R, Lan Y, Huang G B, Xu Z B, Soh Y C. Dynamic extreme learning machine and its approximation capability. IEEE Transactions on Cybernetics, 2013, 43(6): 2054-2065.
Feng G, Lan Y, Zhang X et al. Dynamic adjustment of hidden node parameters for extreme learning machine. IEEE Transactions on Cybernetics, 2015, 45(2): 279-288.
Yang Y,Wu Q M J. Extreme learning machine with subnetwork hidden nodes for regression and classification. IEEE Transactions on Cybernetics, 2016, 46(12): 2885-2898.
[31] Huang G B, Chen L. Convex incremental extreme learning machine. Neurocomputing, 2007, 70(16/17/18): 3056-3062.
[32] Huang G B, Chen L. Enhanced random search based incremental extreme learning machine. Neurocomputing, 2008, 71(16/17/18): 3460-3468.
Xu Z, Yao M, Wu Z, Dai W. Incremental regularized extreme learning machine and it’s enhancement. Neurocomputing, 2016, 174: 134-142.
Kolmogorov A N, Fomin S V. Elements of the Theory of Functions and Functional Analysis: Measure. Graylock Press, 1961.
Kwok T Y, Yeung D Y. Objective functions for training new hidden units in constructive neural networks. IEEE Transactions on Neural Networks, 1997, 8(5): 1131-1148.
Micchelli C A. Interpolation of scattered data: Distance matrices and conditionally positive definite functions. Constructive Approximation, 1986, 2: 11-22.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
ESM 1
(PDF 51 kb)
Rights and permissions
About this article
Cite this article
Wu, YX., Liu, D. & Jiang, H. Length-Changeable Incremental Extreme Learning Machine. J. Comput. Sci. Technol. 32, 630–643 (2017). https://doi.org/10.1007/s11390-017-1746-7
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11390-017-1746-7