BP神经网络的改进及应用  

Improvement and Application of BP Neural Network

作　　者：王立柱[1] 赵大宇[1] 

机构地区：[1]沈阳师范大学数学与系统科学学院,辽宁沈阳110034

出　　处：《沈阳师范大学学报（自然科学版）》2007年第1期61-64,共4页Journal of Shenyang Normal University:Natural Science Edition

摘　　要：合理的选择网络结构是BP神经网络研究中一个重要问题.对传统的BP网络结构进行了改进,在确定BP网络的隐层节点个数时给出了BP网络结构的自适应算法,使得隐层节点的选取动态实现,增强了BP神经网络的适应能力.并应用改进后的BP网对高校教学工作水平评估体系进行建模,为高校教学管理决策提供了科学依据.In BP neural network one question is how to construct a reasonable neural network configuration. An improved method to modeling is presented in this paper. During the course of determining the number of nodes in the hidden units of BP network, the self-adapting algorithm of BP neural network has been proposed and it makes the selection of hidden units dynamically and improves the adaptive ability of net work. At last, the model of artificial neural network for evaluation of college teaching conditions is established by the improved BP neural network, it provides scientific basis for the decision of higher-education management.

关 键 词：人工神经网络 BP算法 学习速率 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]