Skip to main content
SpringerLink
Log in

A Kind of Parameters Self-adjusting Extreme Learning Machine

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Extreme learning machine (ELM) is a kind of feed-forward single hidden layer neural network, whose input weights and thresholds of hidden layers are generated randomly. Because the output-weights of ELM are calculated by the least-square method, the ELM presents a high speed on training and testing. However, the random input-weights and thresholds of hidden layers are not the best parameters, which can not pledge the training goals of the ELM to achieve the global minimum. In order to obtain the optimal input-weights and bias of hidden layer, this paper proposes the self-adjusting extreme learning machine, called SA-ELM. Based on the idea of the ameliorated teaching learning based optimization, the input-weights and the bias of hidden layer of extreme learning machine are adjusted with “teaching phase” and “learning phase” to minimize the objective function values. The SA-ELM is applied to the eight benchmark functions to test its validity and feasibility. Compared with ELM and fast learning network, the SA-ELM owns good regression accuracy and generalization performance. Besides, the SA-ELM is applied to build the thermal efficiency model of a 300 MW pulverized coal furnace. The experiment results reveal that the proposed algorithm owns engineering practical application value.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Salakhutdinov R, Larochelle H (2010) Efficient learning of deep Boltzmann machines. In: International conference on artificial intelligence and statistics, pp 693–700

  2. Vapnik V (2000) The nature of statistical learning theory. Springer, Berlin

    Book  MATH  Google Scholar 

  3. Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural network. In: Proceedings of IEEE international joint conference on neural network, vol 2, pp 985–990

  4. Wang SC (2003) Artificial neural network. Interdisciplinary computing in Java programming. Springer, Heidelberg

    Book  Google Scholar 

  5. Li L, Liu D, Ouyang J (2012) A new regularization classification method based on extreme learning machine in network data. J Inf Comput Sci 9(12):3351–3363

    Google Scholar 

  6. Karpagachelvi S, Arthanari M, Sivakumar M (2012) Classification of electrocardiogram signals with support vector machines and extreme learning machine. Neural Comput Appl 21(6):1331–1339

    Article  Google Scholar 

  7. Yu J, Rui Y, Tang YY et al (2014) High-order distance-based multiview stochastic learning in image classification. IEEE Trans Cybern 44(12):2431–2442

    Article  Google Scholar 

  8. Yu J, Hong R, Wang M et al (2014) Image clustering based on sparse patch alignment framework. Pattern Recognit 47(11):3512–3519

    Article  Google Scholar 

  9. Lan Y, Soh YC, Huang GB (2010) Two-stage extreme learning machine for regression. Neurocomputing 73(16–18):3028–3038

    Article  Google Scholar 

  10. Tang X, Han M (2009) Partial Lanczos extreme learning machine for singal-output regression problems. Neurocomputing 72(13–15):3066–3076

    Article  Google Scholar 

  11. Mikolov T, Chen K, Corrado G et al (2013) Efficient estimation of word representations in vector space. arXiv preprint. arXiv:1301.3781

  12. Zong W, Huang GB (2011) Face recognition based on extreme learning machine. Neurocomputing 74(16):2541–2551

    Article  Google Scholar 

  13. Pan C, Park DS, Yang Y et al (2012) Leukocyte image segmentation by visual attention and extreme learning machine. Neural Comput Appl 21(6):1217–1227

    Article  Google Scholar 

  14. Yu J, Hong R, Wang M et al (2014) Image clustering based on sparse patch alignment framework. Pattern Recognit 47(11):3512–3519

    Article  Google Scholar 

  15. Yu J, Rui Y, Tao D (2014) Click prediction for web image reranking using multimodal sparse coding. IEEE Trans Image Process 23(5):2019–2032

    Article  MathSciNet  Google Scholar 

  16. Wu S, Wang Y, Cheng S (2013) Extreme learning machine based wind speed estimation and sensorless control for wind turbine power generation system. Neurocomputing 102:163–175

    Article  Google Scholar 

  17. Luo Y, Tang J, Yan J et al (2014) Pre-trained multi-view word embedding using two-side neural network. In: Twenty-eighth AAAI conference on artificial intelligence

  18. Yu J, Tao D (2013) Modern machine learning techniques and their applications in cartoon animation research. Wiley, Hoboken

    Book  Google Scholar 

  19. Cao JW, Lin ZP, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36:285–305

    Article  Google Scholar 

  20. Zhu QY, Qin AK, Suganthan PN, Huang GB (2005) Evolutionary extreme learning machine. Pattern Recognit 38:1759–1763

    Article  MATH  Google Scholar 

  21. Matias T, Souza F, Araujo R, Antunes CH (2014) Learning of a single-hidden layer feedforward neural network using an optimized extreme learning machine. Neurocomputing 129:428–436

    Article  Google Scholar 

  22. Han F, Yao HF, Ling QH (2013) An improved evolutionary extreme learning machine based on particle swarm optimization. Neurocomputing 116:87–93

    Article  Google Scholar 

  23. Li GQ, Niu PF, Ma YP, Wang HB, Zhang WP (2014) Tuning extreme learning machine by an improved artificial bee colony to model and optimize the boiler efficiency. Knowl Based Syst 67:278–289

    Article  Google Scholar 

  24. Li GQ, Niu PF, Liu C, Zhang WP (2012) Enhanced combination modeling method for combustion efficiency in coal-fired boilers. Appl Soft Comput 12:3132–3140

    Article  Google Scholar 

  25. Li GQ, Niu PF, Zhang WP, Liu YC (2013) Model NOx emissions by least squares support vector machine with tuning based on ameliorated teaching-learning-based optimization. Chemom Intell Lab Syst 126:11–20

    Article  Google Scholar 

  26. Li GQ, Niu PF, Duan XL, Zhang XY (2013) Fast learning network: a novel artificial neural network with a fast learning speed. Neural Comput Appl. doi:10.1007/s00521-013-1398-7

  27. Liang NY, Huang gb, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17:1411–1423

    Article  Google Scholar 

  28. Rao RV, Savsani VJ, Vakharia DP (2011) Teaching-learning-based optimization: a novel method for constrained mechanical design optimization problems. Comput Aided Des 43(3):303–315

    Article  Google Scholar 

  29. Zhou H, Zhao JP, Zheng LG, Wang CL, Cen KF (2012) Modeling NOx emissions from coal-fired utility boilers using support vector regression with ant colony optimization. Eng Appl Artif Intell 25:147–158

    Article  Google Scholar 

  30. Song Z, Kusiak A (2007) Constraint-based control of boiler efficiency: a data-mining approach. IEEE Trans Ind Inform 3(1):73–83

    Article  Google Scholar 

Download references

Acknowledgments

Project supported by the National Natural Science Foundation of China (Grant No. 61573306, 61403331).

Author information

Authors and Affiliations

  1. Key Laboratory of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, 066004, China

    Peifeng Niu, Yunpeng Ma, Mengning Li & Guoqiang Li

  2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Qinhuangdao, China

    Peifeng Niu & Guoqiang Li

  3. Hydropower Station of Administration of Taolinkou Reservoir, Qinhuangdao, China

    Shanshan Yan

Authors
  1. Peifeng Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yunpeng Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengning Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shanshan Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Guoqiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yunpeng Ma.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Niu, P., Ma, Y., Li, M. et al. A Kind of Parameters Self-adjusting Extreme Learning Machine. Neural Process Lett 44, 813–830 (2016). https://doi.org/10.1007/s11063-016-9496-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-016-9496-z

Keywords

Search

Navigation