基于交叉验证的BP算法的改进与实现  

Improvement of BP algorithm based on cross-validation method and its implementation

作　　者：韩萌[1] 丁剑[1] 

机构地区：[1]西北第二民族学院计算机科学与技术系

出　　处：《计算机工程与设计》2008年第14期3738-3739,3742,共3页Computer Engineering and Design

摘　　要：针对BP算法存在的收敛速度慢等问题提出改进方案,修改其相关参数并且提出如何选择合适的隐藏层节点个数。同时针对学习样本数据的有限性、BP算法易陷入局部最小值和容易出现过拟合等问题进行了研究,提出了采用多重交叉验证的再改进BP算法。仿真结果表明,交叉验证BP算法提高了网络学习的效率。BP algorithm exists against the slow convergence and other problem, in order to improve the program, the system amends its relevant parameters and presents the method to choose a suitable number of hidden layer nodes. Focus on learning ofthe limited nature of the data sample and BP algorithm easy to fall into the local minimum and prone to over-fit problems, the system presented by multiple cross-validation method. The simulation results show that cross-validation BP algorithm improved the efficiency of learning.

关 键 词：神经网络 BP算法 交叉验证 过拟合 隐藏层 误差函数 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]