Sigma-Pi-Sigma神经网络的带动量项梯度算法的收敛性  

Algorithm Convergence of Gradient Method with Momentum for Sigma-Pi-Sigma Neural Network

作　　者：张迅 ZHANG Xun(College of Mathematics, Physics and Electronic Information Engineering, Wenzhou University, Wenzhou, China 32503)

机构地区：[1]温州大学数理与电子信息工程学院,浙江温州325035

出　　处：《温州大学学报（自然科学版）》2018年第2期17-21,共5页Journal of Wenzhou University(Natural Science Edition)

基　　金：国家自然科学基金项目(61572018);浙江省自然科学基金项目(LY15A010016)

摘　　要：对Sigma-Pi-Sigma神经网络(简称SPSNN)的固定学习率梯度算法,引入动量项更新,以期待改善其收敛性.在可变动量项因子的情形,对带动量项的梯度算法进行了确定型收敛性的研究,给出了误差函数的单调性结果,并得到了该算法的弱收敛性定理.This paper probes into a gradient algorithm of the fixed learning rate for Sigma-Pi-Sigma neural network （SPSNN）. The momentum renewal is introduced in order to improve its convergence. Under the situation of variable momentum factor, the gradient algorithm with momentum is studied to confirm its convergence and the result of error function monotony is offered as well. All in all, the weak convergence theorem for this algorithm is obtained.

关 键 词：Sigma-Pi-Sigma神经网络 动量项 梯度算法 收敛性 

分 类 号：O241.6[理学—计算数学]