Abstract
Based on the probability theory and polynomial interpolation and approximation theory, a two-input Gegenbauer orthogonal neural network (TIGONN) is investigated and constructed in this paper. In order to avoid inherent problems of back-propagation (BP) training algorithm, a weights-direct-determination (WDD) is applied to calculate the optimal connecting weights of TIGONN proposed. Then, based on WDD, a growing and pruning weights and structure determination (GPWSD) is developed to determine the optimal connecting weights and optimal number of neurons in hidden layer, by combining growing weights and structure determination (GWSD) and post-pruning scheme. Furthermore, numerical verifications are also conducted to substantiate the superiority and efficacy of TIGONN with GPWSD in terms of approximation and denoising.
Supported by the National Key R&D Program of China under Grant 2017YFB1002505, National Natural Science Foundation of China under Grants 61603142 and 61633010, Guangdong Foundation for Distinguished Young Scholars under Grant 2017A030306009, The Guangdong Youth Talent Support Program of Scientific and Technological Innovation under Grant 2017TQ04X475, the Fundamental Research Funds for Central Universities under Grant 2017MS049, National Key Basic Research Program of China (973 Program) under Grant 2015CB351703.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, G.P.: Neural networks for classification: a survey. IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev. 30(4), 451–462 (2000)
Cenggoro, T.W., Kridalaksana, A.H., Arriyanti, E., Ukkas, M.I.: Recognition of a human behavior pattern in paper rock scissor game using backpropagation artificial neural network method. In: Proceedings of the 2nd International Conference on Information and Communication Technology (ICoICT), pp. 238–243 (2014)
Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing. The MIT Press, Cambridge (1986)
Wan, Y., Wu, C.W.: Fitting and prediction for crack propagation rate based on machine learning optimal algorithm. In: 2009 International Conference on E-Learning, E-Business, Enterprise Information Systems, and E-Government, vol. 1, pp. 96–96 (2009)
Zhang, Y., Zhong, T., Li, W., Xiao, X., Yi, C.: Growing algorithm of laguerre orthogonal basis neural network with weights directly determined. In: Huang, D.-S., Wunsch, D.C., Levine, D.S., Jo, K.-H. (eds.) ICIC 2008. LNCS (LNAI), vol. 5227, pp. 60–67. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85984-0_8
Zhang, L., Suganthan, P.N.: A survey of randomized algorithms for training neural networks. Inf. Sci. 364, 146–155 (2016)
Yu, X.H., Chen, G.A.: Euler neural network with its weight-direct-determination and structure-automatic-determination algorithms. In: Ninth International Conference on Hybrid Intelligent Systems, pp. 319–324 (2009)
Zhang, N.Y., Y, X.T., Lin, X., Li, W.B., Fan, Z.P.: Weights and structure determination of artificial neuronets. Self-organ. Theor. Methods 5370, 109–154 (2014)
Wang, F., Li, H.: Towards reliability evaluation involving correlated multivariates under incomplete probability information: a reconstructed joint probability distribution for isoprobabilistic transformation. Struct. Saf. 69(5), 99–110 (2016)
Robert, V.H., Joseph, W.M., Allen, T.C.: Introduction to Mathematical Statistics, 6th edn. Pearson, Upper Saddle River (2003)
Smith, G.K.: Polynomial Approximation. Encyclopedia of Biostatistics, 2nd edn, Armitage, P., Colton, T. (eds.), vol. 6, pp. 4136–4140. Wiley, London (2004)
Lin, C.: Numerical Analysis. Science Press, China (2007)
Zhang, Y.N., Li, W., Yi, C., Chen, K.: A weights-directly-determined simple neural network for nonlinear system identification. In: IEEE International Conference on Fuzzy Systems, pp. 455–460 (2008)
Zhang, Y.N., Yu, X.T., Guo, D.S., Li, J., Fan, Z.P.: Weights and structure determination of feed-forward two-input neural network activated by Chebyshev polynomials of Class 2. In: Proceedings of the 24th Chinese Control and Decision Conference (CCDC), pp. 1100–1105 (2012)
Zhang, Y.N., Chen, J.H., Guo, D.S., Yin, Y.H., Lao, W.C: Growing-type weights and structure determination of 2-input Legendere orthogonal polynomial neuronet. In: Proceedings of IEEE International Symposium on Industrial Electronics, pp. 852–857 (2012)
Lin, C.H., Hsu, H.Y.: Blend recurrent Gegenbauer orthogonal polynomials neural network control of a SynRM servo-drive CVT system using amended artificial bee colony optimization. In: IEEE International Conference on Applied System Innovation (ICASI), pp. 1–4 (2016)
Charles, D.F., Yuan, X.: Orthogonal Polynomials of Several Variables, pp. 112–115. Cambridge University Press, Cambridge (2009)
Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Lechevallier, Y., Saporta, G. (eds.) Proceedings of COMPSTAT, pp. 177–186. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-7908-2604-3_16
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, Z., He, J., Tang, L. (2019). Two-Input Gegenbauer Orthogonal Neural Network with Growing-and-Pruning Weights and Structure Determination. In: Sun, F., Liu, H., Hu, D. (eds) Cognitive Systems and Signal Processing. ICCSIP 2018. Communications in Computer and Information Science, vol 1006. Springer, Singapore. https://doi.org/10.1007/978-981-13-7986-4_26
Download citation
DOI: https://doi.org/10.1007/978-981-13-7986-4_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-7985-7
Online ISBN: 978-981-13-7986-4
eBook Packages: Computer ScienceComputer Science (R0)