[1]潘文婵,刘尚东.BP神经网络的优化研究与应用[J].计算机技术与发展,2019,29(05):74-76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 016]
　PAN Wen-chan,LIU Shang-dong.Optimization Research and Application of BP Neural Network[J].,2019,29(05):74-76.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 016]
点击复制

BP神经网络的优化研究与应用()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年05期
页码:
74-76
栏目:
智能、算法、系统工程
出版日期:
2019-05-10

文章信息/Info

Title:
Optimization Research and Application of BP Neural Network
文章编号:
1673-629X(2019)05-0074-03
作者:
潘文婵; 刘尚东
南京邮电大学 计算机学院,江苏 南京 210023
Author(s):
PAN Wen-chan; LIU Shang-dong
School of Computer Science,Nanjing University of Posts and Telecommunications, Nanjing 210023,China
关键词:
BP神经网络; 学习率; 均方误差; 深度学习
Keywords:
BP neural network; learning rate; mean square error; deep learning
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 05. 016
摘要:
针对 BP 神经网络自身的一些局限性,诸如易陷于局部极小、网络收敛速度慢、训练时间长等,提出一种改进 BP 神经网络的研究方案,通过改变传统的固定学习率,引入动态变化,根据均方误差的变化而改变学习率。 在误差曲面平坦区域增大学习率,在误差变化剧烈的区域减小学习率,从而加快算法的收敛速度,避免陷入局部极小值。 文中在传统 BP 神经网络中使用动态学习速率,并融合参数可调激活函数来改进 BP 神经网络。 采用公认完备、性能优异的 KDD Cup99 数据集,分别对改进算法和传统 BP 算法进行了对比实验。 实验结果表明,与传统 BP 神经网络算法相比,改进算法极大地提高了训练速度,具有训练误差更小、预测精度更高的优点。
Abstract:
Aiming at some limitations of BP neural network,such as easy to be trapped in local minimum,slow convergence speed and long training time,we propose a scheme of improving BP neural network. By changing the traditional fixed learning rate and introducing dynamic change,the learning rate can be changed according to the change of mean square error. The learning rate is increased in the flat area of the error surface,and decreased in the area where the error changes sharply,so as to accelerate the convergence speed of the algorithm and avoid falling into the local minimum. In the traditional BP neural network,we use the dynamic learning rate with the parameter adjustable activation function to improve the BP neural network. The improved algorithm and the traditional BP algorithm are compared by using the KDD Cup99 data set,which is recognized to be complete and excellent in performance. Experiment shows that compared with traditional algorithms based on BP neural network,the proposed method has greatly improved training speed and has the advantages of smaller training error and higher prediction accuracy.

相似文献/References:

[1]王菲露 宋杰 宋杨.BP神经网络在蛋白质二级结构预测中的应用[J].计算机技术与发展,2009,(05):217.
　WANG Fei-lu,SONG Jie,SONG Yang.Application of BP Neural Network in Protein Secondary Structure Prediction[J].,2009,(05):217.
[2]李秉 王凤山 李晓军.一种弹炮结合武器系统作战效能评估方法[J].计算机技术与发展,2009,(06):217.
　LI Bing,WANG Feng-shan,LI Xiao-jun.An Evaluation Method of Operational Effectiveness of Anti - Aircraft Gun Missile Weapon System[J].,2009,(05):217.
[3]贾其燕 王友仁 崔江.一种基于遗传算法的动态电流测试生成方法[J].计算机技术与发展,2009,(06):225.
　JIA Qi-yan,WANG You-ren,CUI Jiang.A Dynamic Current Test Generation Method Based on Genetic Algorithm[J].,2009,(05):225.
[4]王宁.一种基于BP神经网络的即时在线推荐系统[J].计算机技术与发展,2009,(07):230.
　WANG Ning.An Online Recommendation System Based on BP Network[J].,2009,(05):230.
[5]钟以维 徐应涛 张莹.用填充函数法改进的人脸比对算法[J].计算机技术与发展,2009,(08):78.
　ZHONG Yi-wei,XU Ying-tao,ZHANG Ying.Face Comparison Algorithm Based on Filled Function Method[J].,2009,(05):78.
[6]夏玫 陈立潮 王新波.一种提高BP神经网络泛化能力的改进算法[J].计算机技术与发展,2009,(09):62.
　XIA Mei,CHEN Li-chao,WANG Xin-bo.A Modified Algorithm to Improve Generalization Ability of BP Neural Network[J].,2009,(05):62.
[7]洪素惠 吴发成 米红.神经网络自适应PID在吹瓶机中的应用[J].计算机技术与发展,2009,(09):177.
　HONG Su-hui,WU Fa-cheng,MI Hong.Adaptive PID Controller Based on Neural Networks in Stretch Blow Molding[J].,2009,(05):177.
[8]陈虹 梁文彬 李宗宝 董航飞.基于机器人的神经网络预测控制算法[J].计算机技术与发展,2008,(08):65.
　CFIEN Hong,LIANG Wen-bin,LI Zong-bao,et al.A Neural Network Predictive Control Algorithm Based on Robot[J].,2008,(05):65.
[9]张龙 吴江 张德同.基于粗糙集和BP神经网络的天然裂缝识别[J].计算机技术与发展,2008,(11):41.
　ZHANG Long,WU Jiang,ZHANG De-tong.A Method for Natural Fractures Identification Based on Rough Sets Theory and BP Neural Network[J].,2008,(05):41.
[10]胡人君 李坤 吴小培.基于脑电信号的思维任务分类[J].计算机技术与发展,2007,(05):173.
　HU Ren-jun,LI Kun,WU Xiao-pei.Classification for Different Mental Tasks Based on EEG Signals[J].,2007,(05):173.

更新日期/Last Update: 2019-05-10