A Novel Modular Recurrent Wavelet Neural Network and Its Application to Nonlinear System Identification

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.

[1]  Danilo P. Mandic,et al.  On the choice of parameters of the cost function in nested modular RNN's , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  Ioannis B. Theocharis,et al.  Pipelined Recurrent Fuzzy Neural Networks for Nonlinear Adaptive Speech Prediction , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[4]  Liang Li,et al.  Nonlinear adaptive prediction of nonstationary signals , 1995, IEEE Trans. Signal Process..

[5]  Xiangping Zeng,et al.  Adaptive Extended Pipelined Second-Order Volterra Filter for Nonlinear Active Noise Controller , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[6]  Jin Bae Park,et al.  Generalized predictive control based on self-recurrent wavelet neural network for stable path tracking of mobile robots: adaptive learning rates approach , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[7]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[8]  Cheng-Jian Lin,et al.  Prediction and identification using wavelet-based recurrent fuzzy neural networks , 2004, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Xiangping Zeng,et al.  Low-Complexity Nonlinear Adaptive Filter Based on a Pipelined Bilinear Recurrent Neural Network , 2011, IEEE Transactions on Neural Networks.

[10]  Jiashu Zhang,et al.  A Novel Adaptive Nonlinear Filter-Based Pipelined Feedforward Second-Order Volterra Architecture , 2009, IEEE Transactions on Signal Processing.

[11]  Jiashu Zhang,et al.  Pipelined Chebyshev Functional Link Artificial Recurrent Neural Network for Nonlinear Adaptive Filter , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Zongkun Li,et al.  Nonlinear System Identification Based on Recurrent Wavelet Neural Network , 2009, ISNN.

[13]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[14]  Liu Sheng,et al.  A Normalized Adaptive Training of Recurrent Neural Networks With Augmented Error Gradient , 2008, IEEE Transactions on Neural Networks.

[15]  Jiashu Zhang,et al.  Nonlinear dynamic system identification using pipelined functional link artificial recurrent neural network , 2009, Neurocomputing.

[16]  Okyay Kaynak,et al.  Fuzzy Wavelet Neural Networks for Identification and Control of Dynamic Plants—A Novel Structure and a Comparative Study , 2008, IEEE Transactions on Industrial Electronics.

[17]  S. S. Rao,et al.  Recurrent wavelet networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[18]  Xiangping Zeng,et al.  Nonlinear Adaptive Equalizer Using a Pipelined Decision Feedback Recurrent Neural Network in Communication Systems , 2010, IEEE Transactions on Communications.

[19]  Chi-Huang Lu,et al.  Design and Application of Stable Predictive Controller Using Recurrent Wavelet Neural Networks , 2009, IEEE Transactions on Industrial Electronics.

[20]  Ganapati Panda,et al.  Identification of nonlinear dynamic systems using functional link artificial neural networks , 1999, IEEE Trans. Syst. Man Cybern. Part B.