①哈尔滨工业大学329信箱自动控制理论及应用教研室 哈尔滨 150001;②Helsinki University of Technology,Faculty of Electrical Engineering,Laboratory of Signal Processing and Computer Technology（STI）, Otakaari 5A,FIN-02150,Espoo, Finland
A NEW MODIFIED ELMAN NEURAL NETWORK MODEL
Wang Changhong①; Gao Xiaozhi①; Xu Lixin①; Zhuang Xianyi①; Gao Xiaoming②
①Department of Control Engineering, P. O. Box 329, Harbin Institute of Technology Harbin 150001;②Helsinki University of Technology, Faculty of Electrical Engineering,Laboratory of Signal Processing and Computer Technology（STI）,Otakaari 5A,FIN-02150,Espoo, Finland
Abstract：This paper first discusses the structure, principle and learning algorithm of Elman neural network model. A modified Ehnan neural network model is then proposed by adding new adjustable weights between the context nodes and the output nodes to enhance its dynamical character. The corresponding learning algorithm is also derived by using steepest descent principle. Theoretical analysis and simulation results show that this kind of modified Ehnan neural network learns much faster than the original model.
1997, Vol. 19 
