一种构造径向基神经网络的新型IPL算法  

A New IPL Algorithm for Constructing an RBF Network

作　　者：游培寒[1] 王振家[1] 

机构地区：[1]空军工程大学工程学院,陕西西安710038

出　　处：《系统工程与电子技术》2003年第9期1151-1153,共3页Systems Engineering and Electronics

摘　　要：提出了一种新型的IPL(incremental projection learning)算法。该算法通过调整网络参数,达到修正IPL 算子A的目的。与原来的IPL算法相比,新算法所需训练样本数较少,步骤简单,训练速度快。仿真结果表明,由 经过改进的。IPL算法得到的径向基网络结构相对简单,结果也较精确。In this paper a new incremental projection leaming( IPL) algorithm is presented. Through the network parameter adjustment, this new algorithm can adjust the operator A of IPL. It needs a small number of sampling data, and its training speed is higher than the traditional one. The new IPL algorithm is utilized to produce an RBF network. The computer simulation results show that the structure of the network constructed by the new algorithm is simple and the output of the system is accurate.

关 键 词：IPL算法 RBF神经网络 三段训练法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]