一种大规模小波神经网络的拟牛顿学习算法  

A Quasi-Newton Learning Algorithm of Large Scale Wavelet Neural Network

作　　者：甘旭升[1] 端木京顺[2] 高建国[2] 

机构地区：[1]西京学院基础部,陕西西安710123 [2]空军工程大学装备管理与安全工程学院,陕西西安710038

出　　处：《昆明理工大学学报（自然科学版）》2013年第6期54-60,共7页Journal of Kunming University of Science and Technology(Natural Science)

基　　金：陕西省自然科学基金项目(2007F49)

摘　　要：为解决大规模小波神经网络的优化问题,提出了一种快速的拟牛顿学习算法,即使用改进Wolfe线搜索的仅存储梯度向量拟牛顿算法.该算法每次迭代中最多计算两次梯度,并且计算中仅需存储递度向量,避开了近似Hessian矩阵的存储问题,从而大大降低了计算量和存储需求.仿真验证了算法的有效性和可行性.To solve the optimization problem of large scale wavelet neural network, a fast Quasi - Newton learn- ing algorithm, which only saves gradient vector Quasi -Newton algorithm by using an improved Wolfe line search, is proposed. In every iteration step, the algorithm needs to calculate two gradients at most, and only saves the gradient vector rather than Hessian approximation matrix, which can reduce the computation and mere- ory requirements. Its validity and feasibility are proved by the simulations

关 键 词：小波 神经网络 无约束最优化问题 拟牛顿算法 WOLFE线搜索 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]