Legendre正交基前向神经网络的权值直接确定法  

Weights immediate determination for feed-forward neural network with Legendre orthogonal basis function

作　　者：张雨浓[1] 刘巍[2] 易称福[1] 李巍[1] 

机构地区：[1]中山大学电子与通信工程系,广州510275 [2]中山大学软件学院,广州510275

出　　处：《大连海事大学学报》2008年第1期32-36,共5页Journal of Dalian Maritime University

基　　金：国家自然科学基金资助项目(60643004)

摘　　要：为避免权值反复迭代修正的冗长BP训练过程,避免传统方法陷入局部极小点,根据多项式理论,构造了一种新型前向神经网络模型,推导了基于最速下降法的误差反传算法和基于伪逆的直接确定法.仿真结果显示,迭代方法和伪逆直接确定法都能达到比较高的工作精度(10-6).To avoid lengthy iterative BP-training and its localminima problem, a feed-forward neural network was developed using Legendre orthogonal polynomial activation function based on polynomial interpolation and curve-fitting theory. The neural weights-updating formula was derived by adopting the standard BP training method, and then a pseudo-inverse based method was proposed. Simulation results show that one-step weights-determination method could efficiently achieve at least equally small computational error （10^-6） compared with iterative-training method.

关 键 词：正交多项式 Legendre正交基 标准BP算法 伪逆 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]