A Kind of Extreme Learning Machine Based on Memristor Activation Function

  • Hanman Li
  • Lidan WangEmail author
  • ShuKai Duan
Conference paper
Part of the Proceedings in Adaptation, Learning and Optimization book series (PALO, volume 10)


Extreme learning machine is a new type of algorithm for single hidden layer feedforward neural network. Compared with the traditional algorithms, ELM avoids long time iteration and has the advantages of high speed, small errors. Among them, the activation function plays an important role in the system. Whereas the general ELM usually uses Sigmod function as the activation function, a new kind ELM using memristor’s memristance-charge function as activation function is proposed in this article. Experiments show that, compared with the ELM and the traditional neural network algorithms, the extreme learning machine based on memristance-charge activation function can shorten the time and improve the accuracy. In a word, it has better classification and regression performances.


Extreme learning machine Memristance-charge function Regression and classification performances 


  1. 1.
    Zheng, Y.X.: SVM parameter optimization based on hybrid bionic algorithm. J. Guangxi Norm. Univ. 29(2), 114–118 (2011)Google Scholar
  2. 2.
    Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE International Joint Conference on Neural Networks, Proceedings IEEE, vol. 2, pp. 985–990 (2005)Google Scholar
  3. 3.
    Chua, L.O.: Memristor-the missing circuit element. IEEE Trans. Circ. Theor. 18(5), 507–519 (1971) CrossRefGoogle Scholar
  4. 4.
    Strukov, D.B., Snider, G.S., Stewart, D.R., Williams, R.S.: The missing memristor found. Nature 453(7191), 8083 (2008)CrossRefGoogle Scholar
  5. 5.
    Pershin, Y.V., Di, V.M.: Spin memristive systems: spin memory effects in semiconductor spintronics. Phys. Rev. B 78(11), 113309 (2008)Google Scholar
  6. 6.
    Zong, W., Huang, G.B., Chen, Y.: Weighted extreme learning machine for imbalance learning. Neurocomputing 101(3), 229–242 (2013) CrossRefGoogle Scholar
  7. 7.
    Geng, Z.Q., Qin, L., Han, Y.M., et al.: Energy saving and prediction modeling of petrochemical industries: a novel ELM based on FAHP. Energy 122, 350–362 (2017)CrossRefGoogle Scholar
  8. 8.
    Bi, W.C.: A particle swarm optimization based on extreme learning machine. J. Zhengzhou Univ. 45(1), 100–104 (2013)Google Scholar
  9. 9.
    Zong, W., Huang, G.B.: Face recognition based on extreme learning machine. Neurocomputing 74(16), 2541–2551 (2011)CrossRefGoogle Scholar
  10. 10.
    Huang, G.B., Zhou, H., Ding, X., et al.: Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern. 42(2), 513–529 (2012)Google Scholar
  11. 11.
    Liang, N.Y., Huang, G.B., Saratchandran, P., et al.: A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans. Neural Netw. 17(6), 1411–1423 (2006)CrossRefGoogle Scholar
  12. 12.
    Samat, A., Du, P., Liu, S., et al.: Ensemble extreme learning machines for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 7(4), 1060–1069 (2014)CrossRefGoogle Scholar
  13. 13.
    Bi, H.Y.: The extreme learning machine application in handwritten numeral recognition. Zhengzhou University (2014)Google Scholar
  14. 14.
    Wang, L., Drakakis, E., Duan, S., et al.: Memristor model and its application for chaos generation. Int. J. Bifurc. Chaos 22(8), 241–252 (2012)CrossRefGoogle Scholar
  15. 15.
    Strukov, D.B., Snider, G.S., Stewart, D.R., et al.: The missing memristor found. Nature 453(7191), 80–83 (2008)CrossRefGoogle Scholar
  16. 16.
    Liu, P.: Research on image classification algorithm based on ELM. China Jiliang University (2012)Google Scholar
  17. 17.
    Yaming, Xu, Lidan, Wang, Shukai, Duan: Magnetron TiO2 memristor chaotic system and FPGA hardware implementation. Phys. Sci. J. 65(12), 62–74 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.The College of Electronic and Information EngineeringSouthwest UniversityChongqingChina
  2. 2.National and Local Joint Engineering Laboratory of Intelligent Transmission and Control TechnologySouthwest UniversityChongqingChina
  3. 3.Brain-Inspired Computing and Intelligent Control of Chongqing Key LabSouthwest UniversityChongqingChina

Personalised recommendations