Abstract
To reduce the computational complexity and improve the performance of the recurrent wavelet neural network (RWNN), a novel modular recurrent neural network based on the pipelined architecture (PRWNN) with low computational complexity is presented in this paper. Its modified adaptive real-time recurrent learning (RTRL) algorithm is derived on the gradient descent approach. The PRWNN comprises a number of RWNN modules that are cascaded in a chained form and inherits the modular architectures of the pipelined recurrent neural network (PRNN) proposed by Haykin and Li. Since those modules of the PRWNN can be performed simultaneously in a pipelined parallelism fashion, it would result in a significant improvement in computational efficiency. And the performance of the PRWNN can be also further improved. Computer simulations have demonstrated that the PRWNN provides considerably better performance compared to the single RWNN model for nonlinear dynamic system identification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Narendra KS, Parthasarathy K (1990) Identification and control of dynamical systems using neural networks. IEEE Trans Neural Networks 1(1):4–27
Park J, Sandberg IW (1991) Universal approximation using radial basis function networks. Neural Comput 3:246–257
Patra JC, Pal RN, Chatterji BN, Panda G (1999) Identification of nonlinear dynamic systems using functional link artificial neural network. IEEE Trans Syst Man Cybern B 29(2):254–262
Wu YL, Song Q, Liu S (2008) A normalized adaptive training of recurrent neural networks with augmented error gradient. IEEE Trans Neural Networks 19(2):351–356
Zhang Q, Benviste A (1992) Wavelet networks. IEEE Trans Neural Networks 3(6):889–898
Rao SS, Kumthekar B (1993) Recurrent wavelet networks. In: Proceedings of the 1993 IEEE-SP Workshop IEEE, vol III, pp 3143–3147
Zhao F, Hu L, Li Z (2009) Nonlinear system identification based on recurrent wavelet neural network. In: ISNN 2009, vol 56, pp 517–525
Lu CH (2009) Design and application of stable predictive controller using recurrent wavelet neural networks. IEEE Trans Ind Electron 56(9):3733–3742
Yoo SJ, Choi YH, Park JB (2006) Generalized predictive control based on self-recurrent wavelet neural network for stable path tracking of mobile robots: adaptive learning rates approach. IEEE Trans Circuits Syst I Regul Pap 53(6):1381–1394
Abiyev RH, Kaynak O (2008) Fuzzy wavelet neural networks for identification and control of dynamic plants-a novel structure and a comparative study. IEEE Trans Ind Electron 55(8):3133–3140
Lin C, Chin C (2004) Prediction and identification using wavelet-based recurrent fuzzy neural networks. IEEE Trans Syst Man Cybern B Cybern 34(5):2144–2154
Haykin S, Li L (1995) Nonlinear adaptive prediction of nonstationary signals. IEEE Trans Signal Process 43(2):526–535
Mandic DP, Chambers JA (2000) On the choice of parameters of the cost function in nested modular RNNs. IEEE Trans Neural Networks 11(2):315–322
Zhao HQ, Zhang JS (2009) Nonlinear dynamic system identification using pipelined functional link artificial recurrent neural network. Neurcomputing 72:3046–3054
Stavrakoudis DG, Theocharis JB (2007) Pipelined recurrent fuzzy neural networks for nonlinear adaptive speech prediction. IEEE Trans Syst Man Cybern B Cybern 37(5):1305–1320
Zhao HQ, Zeng XQ, He ZY, Jin WD, Li TR (2012) Adaptive extended pipelined second-order Volterra filter for nonlinear active noise controller. IEEE Trans Audio Speech Lang Process 20(4):1394–1399
Zhao HQ, Zeng XQ, He ZY (2011) Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network. IEEE Trans Neural Networks 22(9):1494–1507
Zhao HQ, Zhang JS (2010) Pipelined Chebyshev functional link artificial recurrent neural network for nonlinear adaptive filter. IEEE Trans Syst Man Cybern B Cybern 40(1):162–172
Zhao HQ, Zeng XQ, Zhang JS, Li TR (2010) Nonlinear adaptive equalizer using a pipelined decision feedback recurrent neural network in communication systems. IEEE Trans Commun 58(8):2193–2198
Zhao HQ, Zhang JS (2009) A novel adaptive nonlinear filter-based pipelined feedforward second-order Volterra architecture. IEEE Trans Signal Process 57(1):237–246
Acknowledgments
This work was partially supported by the National Science Foundation of People’s Republic of China (grant no: 61271340 and 61071183), Sichuan Provincial Youth Science and Technology Fund (grant no. 2012JQ0046), and Fundamental Research Funds for the Central Universities under grant SWJTU12CX026.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhao, H., Zeng, X. (2014). A Novel Modular Recurrent Wavelet Neural Network and Its Application to Nonlinear System Identification. In: Sun, F., Li, T., Li, H. (eds) Foundations and Applications of Intelligent Systems. Advances in Intelligent Systems and Computing, vol 213. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37829-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-37829-4_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37828-7
Online ISBN: 978-3-642-37829-4
eBook Packages: EngineeringEngineering (R0)