Multi-innovation identification algorithm of neural network based on generalized objective function

被引：0

作者：

机构：

[1] College of Geophysics and Information Engineering in China University of Petroleum

来源：

Xu, B.-C. (xbcyl@163.com) | 1600年 / University of Petroleum, China卷 / 37期

关键词：

Generalized objective function; Multi-innovation; Neural network; System identification;

D O I：

10.3969/j.issn.1673-5005.2013.02.027

中图分类号：

学科分类号：

摘要：

To improve the identification accuracy and robustness to noise of dynamic neural network learning algorithm, multi-innovation identification algorithm based on a generalized objective function was presented. The generalized function based on multi-innovation theory was constructed by combining an auxiliary constraint term with the least mean square error. The weight matrix of output layer was trained using the generalized function. The recursive equations for training weight matrix of output layer were derived using Newton iterative algorithm. Compared with the existed second-order learning algorithm, this algorithm has stronger robustness, better convergent rate and accuracy. Simulation results show the efficiency of the new algorithm.

引用

页码：165 / 169

页数：4

共 14 条

[1]

Rojas I., Pomares H., Bernier J.L., Et al., Time series analysis using normalized PG-RBF network with regression weights, Neurocomputing, 42, 1-4, pp. 267-285, (2002)

[2]

Lacy S.L., Bemstein D.S., Subspace identification for non-linear systems with measured-input non-linearities, International Journal of Control, 78, 12, pp. 906-925, (2005)

[3]

Zapranis A., Alexandridis A., model identification in wavelet neural networks framework, Proceedings of the 5th IFIP Conference on Artificial Intelligence Applications & Innovations, Thessaloniki, Greece, April 23-25, 2009, (2009)

[4]

Hua C.-Q., Wang C.-M., Geng Y.-F., Et al., Wet gas flow metering correction model of slotted orifice based on neural network, Journal of China University of Petroleum (Edition of Natural Science), 33, 6, pp. 152-156, (2009)

[5]

Singh Y.P., Roychowdhury P., Dynamic tunneling based regularization in feedforward neural networks, Artificial Intelligence, 131, 1-2, pp. 55-71, (2001)

[6]

Konstantinos P.F., Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms, Neural Networks, 18, 7, pp. 934-950, (2005)

[7]

Yu J.B., Wang S.J., Xi L.F., Evolving artificial neural networks using an improved PSO and DPSO, Neurocomputing, 71, 4-6, pp. 1054-1060, (2008)

[8]

Shao H.-M., An F.-X., A class of gradient algorithms with variable learning rates and convergence analysis for feedforward neural networks training, Journal of China University of Petroleum (Edition of Natural Science), 34, 4, pp. 176-178, (2010)

[9]

Chen D.S., Ramesh C.J., A robust back propagation learning algorithm for function approximation, IEEE Trans on Neural Networks, 5, 3, pp. 467-479, (1994)

[10]

Xu B.-C., Luo X.-L., Wang J.-S., A novel neural network training algorithm based on generalized objective function, Journal of China University of Petroleum (Edition of Natural Science), 33, 6, pp. 95-99, (2009)

← 1 2 →