计算机应用研究2011，Vol.28Issue(11)：4074-4077,4.DOI:10.3969/j.issn.1001-3695.2011.11.019
Pi-sigma神经网络的乘子法随机单点在线梯度算法
Training Pi-sigma neural network by stochastic simple point online gradient algorithm with Lagrange multiplier method
摘要
Abstract
When the on-line gradient algorithm is used for training Pi-sigma neural netrork, there is a problem that the chosen weights may be very small, resulting in a very slow convergence. The shortcoming can be overcome by the penalty method, but there are the difficulties in numerical solution, caused by the facts that the penalty factor must approach infinity and the absolute value of penalty term is nondifferentiable. Based on Lagrange multipler algorithm, this paper proposed a stochastic simple point on-line gradient algorithm to overcome the deficiencies of small weights and penalty function. Using the optimized theory method, transformed the restrained question into the non-constraint question. Proved the convergence rate and stability of the algorithm. The simulated experimental results indicate that the algorithm is efficient.关键词
Pi-sigma神经网络/梯度算法/乘子法/收敛速度/稳定性Key words
Pi-sigma neural network/ gradient algorithm/ Lagrange multipler method/ convergence rate/ stability分类
信息技术与安全科学引用本文复制引用
喻昕,邓飞,唐利霞..Pi-sigma神经网络的乘子法随机单点在线梯度算法[J].计算机应用研究,2011,28(11):4074-4077,4.基金项目
国家自然科学基金资助项目(60763013) （60763013）
广西人才小高地创新团队计划资助项目(桂教人[2007]71号) （桂教人[2007]71号）
广西大学科研基金资助项目(X081017) （X081017）
