Neural Computing and Applications

, Volume 22, Issue 3–4, pp 541–550 | Cite as

A modified extreme learning machine with sigmoidal activation functions

  • Zhixiang X. Chen
  • Houying Y. Zhu
  • Yuguang G. Wang
Extreme Learning Machine's Theory & Application


This paper proposes a modified ELM algorithm that properly selects the input weights and biases before training the output weights of single-hidden layer feedforward neural networks with sigmoidal activation function and proves mathematically the hidden layer output matrix maintains full column rank. The modified ELM avoids the randomness compared with the ELM. The experimental results of both regression and classification problems show good performance of the modified ELM algorithm.


Feedforward neural networks Extreme learning machine Moore–Penrose generalized inverse 



We would thank Feilong Cao for his suggestions on this paper. The support of the National Natural Science Foundation of China (Nos. 90818020, 10871226, 61179041) is gratefully acknowledged.


  1. 1.
    Cybenko G (1989) Approximation by superposition of sigmoidal function. Math Control Signals Syst 2:303–314MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    Funahashi KI (1989) On the approximate realization of continuous mappings by neural networks. Neural Netw 2:183–192CrossRefGoogle Scholar
  3. 3.
    Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4:251–257CrossRefGoogle Scholar
  4. 4.
    Cao FL, Xie TF, Xu ZB (2008) The estimate for approximation error of neural networks: a constructive approach. Neurocomputing 71:626–630CrossRefGoogle Scholar
  5. 5.
    Cao FL, Zhang YQ, He ZR (2009) Interpolation and rate of convergence by a class of neural networks. Appl Math Model 33:1441–1456MathSciNetMATHCrossRefGoogle Scholar
  6. 6.
    Cao FL, Zhang R (2009) The errors of approximation for feedforward neural networks in the Lp metric. Math Comput Model 49:1563–1572MathSciNetMATHCrossRefGoogle Scholar
  7. 7.
    Cao FL, Lin SB, Xu ZB (2010) Approximation capabilities of interpolation neural networks. Neurocomputing 74:457–460CrossRefGoogle Scholar
  8. 8.
    Xu ZB, Cao FL (2004) The essential order of approximation for neural networks. Sci China Ser F Inf Sci 47:97–112MathSciNetMATHCrossRefGoogle Scholar
  9. 9.
    Xu ZB, Cao FL (2005) Simultaneous L p approximation order for neural networks. Neural Netw 18:914–923MathSciNetMATHCrossRefGoogle Scholar
  10. 10.
    Chen TP, Chen H (1995) Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks. IEEE Trans Neural Netw 6:904–910CrossRefGoogle Scholar
  11. 11.
    Chen TP, Chen H (1995) Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Trans Neural Netw 6:911–917CrossRefGoogle Scholar
  12. 12.
    Hahm N, Hong BI (2004) An approximation by neural networks with a fixed weight. Comput Math Appl 47:1897–1903MathSciNetMATHCrossRefGoogle Scholar
  13. 13.
    Lan Y, Soh YC, Huang GB (2010, April) Random search enhancement of error minimized extreme learning machine. In: ESANN 2010 proceedings, European symposium on artificial neural networks—computational intelligence and machine learning, pp 327–332Google Scholar
  14. 14.
    Huang GB, Babri HA (1998) Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans Neural Netw 9:224–229CrossRefGoogle Scholar
  15. 15.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRefGoogle Scholar
  16. 16.
    Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE international joint conference on neural networks, vol 2, pp 985–990Google Scholar
  17. 17.
    Bartlett PL (1998) 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 44:525–536MathSciNetMATHCrossRefGoogle Scholar
  18. 18.
    Feng G, Huang GB, Lin Q, Gay R (2009) Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Netw 20:1352–1357CrossRefGoogle Scholar
  19. 19.
    Huang GB, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70:3056–3062CrossRefGoogle Scholar
  20. 20.
    Huang GB, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71:3460–3468CrossRefGoogle Scholar
  21. 21.
    Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17:879–892CrossRefGoogle Scholar
  22. 22.
    Wang YG, Cao FL, Yuan YB (2011) A study on effectiveness of extreme learning machine. Neurocomputing 74(16):2483–2490CrossRefGoogle Scholar
  23. 23.
    Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans Neural Netw 14:274–281CrossRefGoogle Scholar
  24. 24.
    Rao CR, Mitra SK (1971) Generalized inverse of matrices and its applications. Wiley, New YorkMATHGoogle Scholar
  25. 25.
    Rätsch G, Onoda T, Müller KR (1998) An improvement of AdaBoost to avoid overfitting. In: Proceedings of the 5th international conference on neural information processing (ICONIP 1998)Google Scholar
  26. 26.
    Romero E, Alquézar R (2002) A new incremental method for function approximation using feed-forward neural networks. In: Proceedings of the 2002 international joint conference on neural networks (IJCNN’2002), pp 1968–1973Google Scholar
  27. 27.
    Serre D (2000) Matrices: theory and applications. Springer, New YorkGoogle Scholar
  28. 28.
    Frank A, Asuncion A (2010) UCI machine learning repository. University of California, School of Information and Computer Science, Irvine.
  29. 29.
    Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Machine learning: proceedings of the 13th international conference, pp 148–156Google Scholar
  30. 30.
    Wilson DR, Martinez TR (1996, June) Heterogeneous radial basis function networks. In: IEEE international conference on neural networks (ICNN’96), pp 1263–1267Google Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  • Zhixiang X. Chen
    • 1
  • Houying Y. Zhu
    • 2
  • Yuguang G. Wang
    • 2
  1. 1.Department of MathematicsShaoxing UniversityShaoxingPeople’s Republic of China
  2. 2.Department of Information and Mathematics SciencesChina Jiliang UniversityHangzhouPeople’s Republic of China

Personalised recommendations