| 改进BP神经网络在个人信用评估系统的应用 |
| |
| 引用本文： | 张冠珠,刘朝东.改进BP神经网络在个人信用评估系统的应用[J].齐齐哈尔大学学报(自然科学版),2008,24(5). |
| |
| 作者姓名： | 张冠珠 刘朝东 |
| |
| 作者单位： | 齐齐哈尔大学计算机控制与工程学院,黑龙江,齐齐哈尔,161006 |
| |
| 摘 要： | 针对一般BP算法收敛速度慢和易陷人局部极小值的缺陷,提出利用一种自适应学习速率动量梯度下降反向传播算法对网络进行训练.该算法使BP神经网络学习速率和稳定性得到提高,并将这种改进的BP网络应用于个人信用评估系统,验证了该方法的正确性和有效性.
|
| 关 键 词： | BP算法 函数梯度 神经网络 |
Improved BP neural networks in personal credit rating system's application |
| |
| ZHANG Guan-zhu,LIU Chao-dong.Improved BP neural networks in personal credit rating system''s application[J].Journal of Qiqihar University(Natural Science Edition),2008,24(5). |
| |
| Authors: | ZHANG Guan-zhu LIU Chao-dong |
| |
| Institution: | ZHANG Guan-zhu LIU Chao-dong (College of Engineering , Computer Control,Qiqihar University,Heilongjiang Qiqihar 161006,Chian) |
| |
| Abstract: | A reverse transmission calculation of self adaptive learning rate with momentum gradient reduction is described in the paper against the problems of slow convergence and easy trapping into smallest spot.The calculation has made the BP net upgrade the rate and stability of learning.BP and the improvement of the network used a personal credit assessment system to verify the correctness of the method and effectiveness. |
| |
| Keywords: | BP algorithm function grads neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
