Elman网络梯度学习法的收敛性  

Convergence of Gradient Method for Elman Networks

作　　者：吴微[1] 徐东坡[1] 李正学[1] 

机构地区：[1]大连理工大学应用数学系,辽宁大连116023

出　　处：《应用数学和力学》2008年第9期1117-1123,共7页Applied Mathematics and Mechanics

基　　金：国家自然科学基金资助项目(10471017)

摘　　要：考虑有限样本集上Elman网络梯度学习法的确定性收敛性.证明了误差函数的单调递减性.给出了一个弱收敛性结果和一个强收敛结果,表明误差函数的梯度收敛于0,权值序列收敛于固定点.通过数值例子验证了理论结果的正确性.The gradient method for training Elman networks with finite training sample set is consid- ered. The monotonicity of the error function in the iteration is shown. A weak and a strong conver-gence 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神经网络 梯度学习算法 收敛性 单调性 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]