Convergence of gradient method for Elman networks  

作　　者：吴微 徐东坡 李正学 

机构地区：[1]Department of Applied Mathematics,Dalian University of Technology

出　　处：《Applied Mathematics and Mechanics(English Edition)》2008年第9期1231-1238,共8页应用数学和力学（英文版）

基　　金：the National Natural Science Foundation of China (No.10471017)

摘　　要：The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.

关 键 词：Elman network gradient learning algorithm CONVERGENCE MONOTONICITY 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]