Abstract
In this chapter, two major issues are addressed: (i) how to obtain a more compact network architecture and (ii) how to reduce the overall computational complexity. An integrated analytic framework is introduced for the fast construction of single-hidden-layer feedforward networks (SLFNs) with two sequential phases. The first phase of the algorithm focuses on the computational efficiency for fast computation of the unknown parameters and fast selection of the hidden nodes. The second phase focuses on improving the performance of the network obtained in the first phase. The proposed algorithm is evaluated on several benchmark problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akaike H (1974) New look at the statistical model identification. IEEE Trans Automat Cont AC-19(1): 716–723
Ampazis N, Perantonis SJ (2002) Two highly efficient second-order algorithms for training feedforward networks. IEEE Trans Neural Netw 13(3): 1064–1074
Bishop CM (1995) Neural networks for pattern recognition. Clarendon Press, Oxford
Blake C, Merz C (1998) UCI repository of machine learning databases. In: Department of Information and Computer Sciences, University of California, Irvine, CA. http://www.ics.uci.edu/∼mlearn/MLRepository.html
Chen S, Wigger J (1995) Fast orthogonal least squares algorithm for efficient subset model selection. IEEE Trans Signal Process 43(7):1713–1715
Chen S, Billings SA, Luo W (1989) Orthogonal least squares methods and their application to non-linear system identification. Int J Control 50(5):1873–1896
Chen S, Cowan CFN, Grant PM (1991) Orthogonal least squares learning algorithm for radial basis functions. IEEE Trans Neural Netw 2:302–309
Chng ES, Chen S, Mulgrew B (1996) Gradient radial basis function networks for nonlinear and nonstationary time series prediction. IEEE Trans Neural Netw 7(1):190–194
Gomm JB, Yu DL (March 2000) Selecting radial basis function network centers with recursive orthogonal least squares training. IEEE Trans Neural Netw 11(2):306–314
Hagan MT, Menhaj MB (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993
Handoko SD, Keong KC, Soon OY, Zhang GL, Brusic V (2006) Extreme learning machine for predicting HLA-peptide binding. Lect Notes Comput Sci 3973:716–721
Hong X, Mitchell RJ, Chen S, Harris CJ, Li K, Irwin G (2008) Model selection approaches for nonlinear system identification: a review. Int J Syst Sci 39(10):925–946
Huang G-B, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70(16–18):3056–3062
Huang G-B, Saratchandran P, Sundararajan N (2005) A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans Neural Netw 16(1):57–67
Huang G-B, Chen L, Siew C-K (2006a) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892
Huang G-B, Zhu Q-Y, Siew C-K (2006b) Extreme learning machine: theory and applications. Neurocomputing 70:489–501
Huang G-B, Zhu Q-Y, Mao KZ, Siew C-K, Saratchandran P, Sundararajan N (2006c) Can threshold networks be trained directly? IEEE Trans Circuits Syst II 53(3):187–191
Kadirkamanathan V, Niranjan M (1993) A function estimation approach to sequential learning with neural networks. Neural Comput 5:954–975
Korenberg MJ (1988) Identifying nonlinear difference equation and functional expansion representations: the fast orthogonal algorithm. Ann Biomed Eng 16:123–142
Lawson L, Hanson RJ (1974) Solving least squares problem. Prentice-Hall, Englewood Cliffs, NJ
Li K, Peng J, Irwin GW (2005) A fast nonlinear model identification method. IEEE Trans Automa Cont 50(8):1211–1216
Li K, Peng J, Bai EW (2006) A two-stage algorithm for identification of nonlinear dynamic systems. Automatica 42(7):1189–1197
Li K, Peng J, Bai E (2009) Two-stage mixed discrete-continuous identification of radial basis function (RBF) neural models for nonlinear systems. IEEE Trans Circuits Syst I Regular Pap 56(3):630–643
Li M-B, Huang G-B, Saratchandran P, Sundararajan N (2005) Fully complex extreme learning machine. Neurocomputing 68:306–314
Liang N-Y, Huang G-B, Saratchandran P, Sundararajan N (2006a) A fast and accurate on-line sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423
Liang N-Y, Saratchandran P, Huang G-B, Sundararajan N (2006b) Classification of mental tasks from EEG signals using extreme learning machine. Int J Neural Syst 16(1):29–38
Liu Y, Loh HT, Tor SB (2005) Comparison of extreme learning machine with support vector machine for text classification. Lect Notes Comput Sci 3533:390–399
Mackey MC, Glass L (1977) Oscillation and chaos in physiological control systems. Science 197:287–289
Mao KZ, Huang G-B (2005) Neuron selection for RBF neural network classifier based on data structure preserving criterion. IEEE Trans Neural Netw 16(6):1531–1540
Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11:431–441
McLoone S, Brown MD, Irwin GW, Lightbody G (1998) A hybrid linear/nonlinear training algorithm for feedforward neural networks. IEEE Trans Neural Netw 9:669–684
Miller AJ (1990) Subset selection in regression. Chapman & Hall, London
Musavi M, Ahmed W, Chan K, Faris K, Hummels D (1992) On training of radial basis function classifiers. Neural Netw 5:595–603
Panchapakesan C, Palaniswami M, Ralph D, Manzie C (2002) Effects of moving the centers in an RBF network. IEEE Trans Neural Netw 13:1299–1307
Peng H, Ozaki T, Haggan-Ozaki V, Toyoda Y (2003) A parameter optimization method for radial basis function type models. IEEE Trans Neural Netw 14:432–438
Peng J, Li K, Huang DS (2006) A hybrid forward algorithm for RBF neural network construction. IEEE Trans Neural Netw 17(11):1439–1451
Peng J, Li K, Irwin GW (2007) A novel continuous forward algorithm for RBF neural modelling. IEEE Trans Automat Cont 52(1):117–122
Peng J, Li K, Irwin GW (2008) A new Jacobian matrix for optimal learning of single-layer neural nets. IEEE Trans Neural Netw 19(1):119–129
Piroddi L, Spinelli W (2003) An identification algorithm for polynomial NARX models based on simulation error minimization. Int J Cont 76:1767–1781
Platt J (1991) A resource-allocating network for function interpolation. Neural Comput 3:213–225
Press WH, Teukolsky SA, Vetterling WT, Flannery BP (1992) Numerical recipes in C: the art of scientific computing. Cambridge University Press, Cambridge
Rao CR, Mitra SK (1971) Generalized inverse of matrices and its applications. Wiley, New York
Serre D (2002) Matrices: theory and applications. Springer, New York
Sutanto EL, Mason JD, Warwick K (1997) Mean-tracking clustering algorithm for radial basis function centre selection. Int J Control 67:961–977
Wang D, Huang G-B (2005) Protein sequence classification using extreme learning machine. In: Proceedings of international joint conference on neural networks (IJCNN2005), Montreal, Canada, 31 July – 4 August 2005
Xu J-X, Wang W, Goh JCH, Lee G (2005) Internal model approach for gait modeling and classification. In: the 27th annual international conference of the IEEE, Engineering in Medicine and Biology Society (EMBS), Shanghai, China, 1–4 September 2005
Yeu C-WT, Lim M-H, Huang G-B, Agarwal A, Ong Y-S (2006) A new machine learning paradigm for terrain reconstruction. IEEE Geosci Rem Sens Lett 3(3):382–386
Yingwei L, Sundararajan N, Saratchandran P (1997) A sequential learning scheme for function approximation using minimal radial basis function (RBF) neural networks. Neural Comput 9:461–478
Zhang GL, Billings SA (1996) Radial basis function network configuration using mutual information and the orthogonal least squares algorithm. Neural Netw 9:1619–1637
Zhang R, Huang G-B, Sundararajan N, Saratchandran P (2007) Multi-category classification using an extreme learning machine for microarray gene expression cancer diagnosis. IEEE/ACM Trans Comput Biol Bioinform 4(3):485–495
Zhu QM, Billings SA (1996) Fast orthogonal identification of nonlinear stochastic models and radial basis function neural networks. Int J Control 64(5):871–886
Acknowledgment
K. Li would like to acknowledge the helpful comments from Lei Chen of the National University of Singapore. He would also like to acknowledge the support of the International Exchange program of Queen's University Belfast.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this entry
Cite this entry
Li, K., Huang, GB., Ge, S.S. (2012). Fast Construction of Single-Hidden-Layer Feedforward Networks. In: Rozenberg, G., Bäck, T., Kok, J.N. (eds) Handbook of Natural Computing. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92910-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-92910-9_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92909-3
Online ISBN: 978-3-540-92910-9
eBook Packages: Computer ScienceReference Module Computer Science and Engineering