论文信息 - A Stable Online Self-Constructing Recurrent Neural Network

A Stable Online Self-Constructing Recurrent Neural Network

A new online self-constructing recurrent neural network (SCRNN) model is proposed, of which the network structure could adjust according to the specific problem in real time. If the approximation performance of SCRNN is insufficient, SCRNN can create new neural network state to increase the learning ability. If the neural network state of SCRNN is redundant, it should be removed to simplify the structure of neural network and reduce the computation load;otherwise, if the hidden neuron of SCRNN is significant, it should be retained. Meanwhile, the feedback coefficient is adjusted by synaptic normalization mechanism to ensure the stability of network state. The proposed method effectively generates a recurrent neural model with a highly accurate and compact structure. Simulation results demonstrate that the proposed SCRNN has a self-organizing ability which can determine the structure and parameters of the recurrent neural network automatically. The network has a better stability.

Junfei Qiao | Wei Chai | Qili Chen

[1] Jeen-Shing Wang,et al. A Wiener-type recurrent neural network and its control strategy for nonlinear dynamic applications , 2009 .

[2] Meng Joo Er,et al. Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear systems , 2003, IEEE Trans. Fuzzy Syst..

[3] Andrzej Janczak. Identification of Nonlinear Systems Using Neural Networks and Polynomial Models , 2005 .

[4] Chun-Fei Hsu. Intelligent position tracking control for LCM drive using stable online self-constructing recurrent neural network controller with bound architecture , 2009 .

[5] Gordon Pipa,et al. SORN: A Self-Organizing Recurrent Neural Network , 2009, Front. Comput. Neurosci..

[6] A. Janczak,et al. Identification of Nonlinear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach , 2004 .

[7] Henk B. Verbruggen,et al. A new method for identification and control of nonlinear dynamic systems , 1996 .

[8] M. J. Korenberg,et al. The identification of nonlinear biological systems: Wiener and Hammerstein cascade models , 1986, Biological Cybernetics.

[9] Olivier D. Faugeras,et al. A Constructive Mean-Field Analysis of Multi-Population Neural Networks with Random Synaptic Weights and Stochastic Inputs , 2008, Front. Comput. Neurosci..

[10] Jang-Hyun Park,et al. Direct adaptive controller for nonaffine nonlinear systems using self-structuring neural networks , 2005, IEEE Transactions on Neural Networks.