计算机工程与应用2013，Vol.49Issue(4)：43-46,4.DOI:10.3778/j.issn.1002-8331.1110-0459
递归pi-sigma神经网络的带惩罚项的梯度算法分析
Gradient algorithm with penalty for training recurrent pi-sigma neural network
摘要
Abstract
In this paper, a new gradient training algorithm is presented to train the recurrent pi-sigma neural networks, in which a penalty is added to the conventional error function. The algorithm can not only improve the generalization of neural networks, but also avoid the slow convergence caused by the case that the original weights are chosen too small, achieving a better convergence compared to the traditional gradient algorithm without the penalty term. Moreover, the convergence of the algorithm is also studied, and finally the simulated experimental results indicates that the algorithm is efficient.关键词
递归pi-sigma神经网络/梯度算法/惩罚项/收敛性Key words
recurrent pi-sigma neural networks/gradient algorithm/penalty/convergence分类
信息技术与安全科学引用本文复制引用
喻昕,邓飞..递归pi-sigma神经网络的带惩罚项的梯度算法分析[J].计算机工程与应用,2013,49(4):43-46,4.基金项目
国家自然科学基金(No.60763013) （No.60763013）
广西人才小高地创新团队计划(No.[2007]71) （No.[2007]71）
广西教育厅基金项目(No.TLZ100715) （No.TLZ100715）
广西大学科研基金项目(No.X081017). （No.X081017）
