Title :
A Novel Recurrent Generalized Congruence Neural Network for Dynamical System Identification
Author :
Yan, Tianyun ; Ling, Hefei ; Zou, Shurong
Author_Institution :
ChengDu Univ. of Inf. Technol., Chengdu
Abstract :
A novel recurrent generalized congruence neural network (RGCNN) is presented. Compared with traditional recurrent neural networks (RNNs), RGCNN has the following advantages: simple structure (4 layers), no time-consuming iterative derivative operations in updating weights, and fast convergence induced by modulo arithmetic of the generalized congruence neuron. Computer simulations on benchmark examples of dynamical system identification have successfully validated the performance of the proposed RGCNN.
Keywords :
identification; recurrent neural nets; convergence; dynamical system identification; generalized congruence neural network; modulo arithmetic; Arithmetic; Artificial neural networks; Convergence; Delay systems; Information technology; Neural networks; Neurons; Nonlinear dynamical systems; Recurrent neural networks; System identification;
Conference_Titel :
Natural Computation, 2007. ICNC 2007. Third International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2875-5
DOI :
10.1109/ICNC.2007.122
