Evolutionary Extreme Learning Machine – Based on Particle Swarm Optimization

  • You Xu
  • Yang Shu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)


A new off-line learning method of single-hidden layer feed-forward neural networks (SLFN) called Extreme Learning Machine (ELM) was introduced by Huang et al. [1, 2, 3, 4] . ELM is not the same as traditional BP methods as it can achieve good generalization performance at extremely fast learning speed. In ELM, the hidden neuron parameters (the input weights and hidden biases or the RBF centers and impact factors) were pre-assigned randomly so there may be a set of non-optimized parameters that avoid ELM achieving global minimum in some applications. Adopting the ideas in [5] that a single layer feed-forward neural network can be trained using a hybrid approach which takes advantages of both ELM and the evolutionary algorithm, this paper introduces a new kind of evolutionary algorithm called particle swarm optimization (PSO) which can train the network more suitable for some prediction problems using the ideas of ELM.


Particle Swarm Optimization Extreme Learn Machine Particle Swarm Optimization Algorithm Input Weight Hybrid Particle Swarm Optimization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, July 25-29 (2004)Google Scholar
  2. 2.
    Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme Learning Machine: Theory and Applications. In: Neurocomputing (2006) (in press)Google Scholar
  3. 3.
    Huang, G.B., Siew, C.K.: Extreme Learning Machine with Randomly Assigned RBF Kernels. International Journal of Information Technology 11 (2005)Google Scholar
  4. 4.
    Huang, G.B., Siew, C.K.: Extreme Learning Machine: RBF Network Case. In: Proceedings of the Eighth International Conference on Control, Automation, Robotics and Vision (ICARCV 2004), Kunming, China, December 6–9 (2004)Google Scholar
  5. 5.
    Zhu, Q.Y., Qin, A., Suganthan, P., Huang, G.B.: Evolutionary Extreme Learning Machine. Pattern Recognition 38, 1739–1763 (2005)CrossRefGoogle Scholar
  6. 6.
    Xu, Y.: A Gradient-Based ELM Algorithm in Regressing Multivariable Functions. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3971, pp. 653–658. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)MATHGoogle Scholar
  8. 8.
    Chau, K.: A Split-Step PSO Algorithm in Prediction of Water Quality Pollution. In: Proceedings of the International Symposium on Neural Networks (2005), Chongqing, China, May 30 - June 1, pp. 1034–1039 (2005)Google Scholar
  9. 9.
    National Bureau of Statistics of China: The Annals (2003) of Statistical Data in China. China Statistics Press, Beijing (2004)Google Scholar
  10. 10.
    Huang, G.B., Zhu, Q.Y., Mao, K.Z., Siew, C.K., Saratchandran, P., Sundararajan, N.: Can Threshold Networks Be Trained Directly? IEEE Transactions on Circuits and Systems - II 53 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • You Xu
    • 1
  • Yang Shu
    • 1
  1. 1.Department of MathematicsNanjing UniversityNanjingP.R. China

Personalised recommendations