nach oben

Neural Computing and Applications

Erschienen in:

01.12.2014 | Original Article

Weights and structure determination of multiple-input feed-forward neural network activated by Chebyshev polynomials of Class 2 via cross-validation

verfasst von: Yunong Zhang, Xiaotian Yu, Dongsheng Guo, Yonghua Yin, Zhijun Zhang

Erschienen in: Neural Computing and Applications | Ausgabe 7-8/2014

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Differing from conventional improvements on backpropagation (BP) neural network, a novel neural network is proposed and investigated in this paper to overcome the BP neural-network weaknesses, which is called the multiple-input feed-forward neural network activated by Chebyshev polynomials of Class 2 (MINN-CP2). In addition, to obtain the optimal number of hidden-layer neurons and the optimal linking weights of the MINN-CP2, the paper develops an algorithm of weights and structure determination (WASD) via cross-validation. Numerical studies show the effectiveness and superior abilities (in terms of approximation and generalization) of the MINN-CP2 equipped with the algorithm of WASD via cross-validation. Moreover, an application to gray image denoising demonstrates the effective implementation and application prospect of the proposed MINN-CP2 equipped with the algorithm of WASD via cross-validation.

Vorheriger Artikel Research for AQM based on MiniMax method

Nächster Artikel Coordinated formation pattern control of multiple marine surface vehicles with model uncertainty and time-varying ocean currents

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Yu S, Zhu K, Diao F (2008) A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction. Appl Math Comput 195:66–75CrossRefMATHMathSciNet

Liang L, Wu D (2005) An application of pattern recognition on scoring Chinese corporations financial conditions based on backpropagation neural network. Comput Oper Res 32:1115–1129CrossRef

Zhang Y, Jiang D, Wang J (2002) A recurrent neural network for solving Sylvester equation with time-varying coefficients. IEEE Trans Neural Netw 13:1053–1063CrossRef

Izeboudjen N, Bouridane A, Farah A, Bessalah H (2012) Application of design reuse to artificial neural networks: case study of the back propagation algorithm. Neural Comput Appl 21:1531–1544CrossRef

Dehuri S, Cho SB (2010) A comprehensive survey on functional link neural networks and an adaptive PSO-BP learning for CFLNN. Neural Comput Appl 19:187–205CrossRef

Wang W, Yu B (2009) Text categorization based on combination of modified back propagation neural network and latent semantic analysis. Neural Comput Appl 18:875–881CrossRef

Zhang Y, Li W, Yi C, Chen K (2008) A weights-directly-determined simple neural network for nonlinear system identification. In: Proceedings of the IEEE international conference on fuzzy systems, pp 455–460

Zhang Y, Li L, Yang Y, Ruan G (2009) Euler neural network with its weight-direct-determination and structure-automatic-determination algorithms. In: Proceedings of the 9th international conference on hybrid intelligent systems, pp 319–324

Zhang Y, Chen J, Guo D, Yin Y, Lao W (2012) Growing-type weights and structure determination of 2-input Legendre orthogonal polynomial neuronet. In: Proceedings of the IEEE international symposium on industrial electronics, pp 852–857

10.

Qin T, Chen Z, Zhang H, Li S, Xiang W, Li M (2004) A learning algorithm of CMAC based on RLS. Neural Process Lett 19:49–61CrossRef

11.

Qin T, Zhang H, Chen Z, Xiang W (2005) Continuous CMAC-QRLS and its systolic array. Neural Process Lett 22:1–16CrossRef

12.

Chen S, Cowan C, Grant P (1991) Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Netw 2:302–309CrossRef

13.

Chen S, Billings S, Luo W (1989) Orthogonal least squares methods and their application to non-linear system identification. Int J Control 50:1873–1896CrossRefMATHMathSciNet

14.

Chen S, Wu Y, Luk B (1999) Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks. IEEE Trans Neural Netw 10:1239–1243CrossRef

15.

Montana D, Davis L (1989) Training feedforward neural networks using genetic algorithms. In: Proceedings of the international joint conferences on artificial intelligence, pp 762–767

16.

Huang G, Zhu Q, Siew C (2006) Extreme learning machine: a new learning scheme of feedforward neural networks. Neurocomputing 70:489–501CrossRef

17.

Bebis G, Georgiopoulos M (1994) Feed-forward neural networks. IEEE Potentials 13:27–31CrossRef

18.

Boyd JP (2000) Chebyshev and Fourier spectral methods, 2nd edn. Dover Publications, New York

19.

Liang X, Li Q (2005) Multivariable approximation. National Defense Industry Press, Beijing

20.

Ibrahim B, Ertan I (2008) Direct and converse results for multivariate generalized Bernstein polynomials. J Comput Appl Math 219:145–155CrossRefMATHMathSciNet

21.

Dunkl C, Xu Y (2001) Orthognal polynomials of several variables. Cambridge University Press, CambridgeCrossRef

22.

Zhang Y, Li K, Tan N (2009) An RBF neural network classifier with centers, variances and weights directly determined. Comput Technol Autom 28:5–9

23.

Zhang Y, Tan N (2010) Weights direct determination of feedforward neural networks without iterative BP-training (chapter 10). In: Wang LS, Hong T (eds) Intelligent soft computation and evolving data mining: integrating advanced technologies. IGI Global, Hershey

24.

Zhang Y, Yu X, Xiao L, Li W, Fan Z (2013) Weights and structure determination of artificial neuronets (chapter 5). In: Zhang WJ (ed) Self-organization: theories and methods. Nova Science, New York

25.

Zhang Y, Li W (2009) Gegenbauer orthogonal basis neural network and its weights-direct-determination method. Electron Lett 45:1184–1185CrossRef

26.

Zhang G, Hu M, Patuwo B, Indro D (1999) Artificial neural networks in bankruptcy prediction general framework and cross-validation analysis. Eur J Oper Res 116:16–32CrossRefMATH

27.

Mi X, Zou Y, Wei W, Ma K (2005) Testing the generalization of artificial neural networks with cross-validation and independent-validation in modelling rice tillering dynamics. Ecol Model 181:493–508CrossRef

28.

Engel J (1996) Choosing an appropriate sample interval for instantaneous sampling. Behav Process 38:11–17CrossRef

29.

Pawlus P, Zelasko W (2012) The importance of sampling interval for rough contact mechanics. Wear 276–277:121–129CrossRef

30.

Ji Z, Chen Q, Sun Q, Xia D (2009) A moment-based nonlocal-means algorithm for image denoising. Inf Process Lett 109:1238–1244CrossRefMATHMathSciNet

31.

Nguyen-Thien T, Tran-Cong T (1999) Approximation of functions and their derivatives a neural network implementation with applications. Appl Math Model 23:687–704CrossRefMATH

32.

Huang G, Saratchandran P, Sundararajan N (2005) A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans Neural Netw 16(1):57–67CrossRef

33.

Gonzalez R, Woods R (2003) Digital image processing, 2nd edn. Publishing House of Electronics Industry, Beijing

34.

http://www.imageprocessingplace.com/

35.

Ibnkahla M (2007) Neural network modeling and identification of nonlinear MIMO channels. In: Proceedings of the 9th international symposium on signal processing and its applications, pp 1–4

36.

Zhang T, Zhou C, Zhu Q (2009) Adaptive variable structure control of MIMO nonlinear systems with time-varying delays and unknown dead-zones. Int J Autom Comput 6:124–136CrossRef

Titel: Weights and structure determination of multiple-input feed-forward neural network activated by Chebyshev polynomials of Class 2 via cross-validation
verfasst von: Yunong Zhang
Xiaotian Yu
Dongsheng Guo
Yonghua Yin
Zhijun Zhang
Publikationsdatum: 01.12.2014
Verlag: Springer London
Erschienen in: Neural Computing and Applications / Ausgabe 7-8/2014
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI: https://doi.org/10.1007/s00521-014-1667-0

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 7-8/2014

Predictions of toughness and hardness by using chemical composition and tensile properties in microalloyed line pipe steels

Nonlinear features of heart rate variability in paranoid schizophrenic

A group decision classifier with particle swarm optimization and decision tree for analyzing achievements in mathematics and science

CFD simulation and optimization of ICEs exhaust heat recovery using different coolants and fin dimensions in heat exchanger

Exponential synchronization of two totally different chaotic systems based on a unified model

A new stochastic search algorithm bundled honeybee mating for solving optimization problems

Premium Partner