[1]邓文杰. 基于聚粒子群算法的神经网络权值优化方法[J].计算机技术与发展,2017,27(10):16-18.
　DENG Wen-jie. A Neural Network Weights Optimization Method Based on Clustering Particle Swarm Optimization[J].,2017,27(10):16-18.
点击复制

 基于聚粒子群算法的神经网络权值优化方法(/HTML)
分享到：

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

卷:
27
期数:
2017年10期
页码:
16-18
栏目:
智能、算法、系统工程
出版日期:
2017-10-10

文章信息/Info

Title:
 A Neural Network Weights Optimization Method Based on Clustering Particle Swarm Optimization
文章编号:
1673-629X（2017)10-0016-03
作者:
 邓文杰
 四川大学 计算机学院
Author(s):
 DENG Wen-jie
关键词:
 ; BP神经网络; 粒子群优化; 聚类; 权值; 局部最优
Keywords:
 ; BP neural networks; particle swarm optimization; clustering; weight; local optimum
分类号:
TP183
文献标志码:
A
摘要:
 神经网络作为机器智能分支中一种优秀的分类算法,在图像分类、人脸识别等领域中都有非常广泛的应用.但由于其参数过多,所以容易陷入局部最优解.针对BP神经网络易陷入局部最优的问题,提出了一种粒子群算法和聚类算法结合的优化神经网络权值的方法.该方法通过把神经网络的权值作为粒子群算法的初始粒子并利用粒子群算法的随机性全局搜索神经网络的待选初始权值,然后利用C均值算法找出包含权值较多的那一类,并把其聚类中心作为BP神经网络的初始权值.仿真结果表明,利用这种新的融合算法在防止BP神经网络易陷入局部最优的问题上能比普通的粒子群算法更加优秀.
Abstract:
 Neural network is a kind of excellent classification algorithm in the branch of machine intelligence,which has a wide range of applications in the field of image classification,face recognition and so on. However,because of its excessive parameters,it is easy to fall into the local optimal solution. According to this problem,a method combining particle swarm algorithm and clustering algorithm to opti-mize the weights of neural networks is proposed,which takes the neural network weights as the initial particle of particle swarm algorithm and uses the random of particle swarm algorithm to search the initial weights of neural network. Then the class contains more weight is found using C-means algorithm and its clustering center is regarded as the initial weights of BP neural network. The simulation results show that it is more excellent than the conventional particle swarm optimization algorithm in preventing the BP neural network from fall-ing into local optimum.

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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):173.
[11]段艳明. 基于PSO算法和BP神经网络的PID控制研究[J].计算机技术与发展,2014,24(08):238.
　DUAN Yan-ming. Research of PID Control Based on BP Neural Network and PSO Algorithm[J].,2014,24(10):238.
[12]朱俚治. 一种基于BP神经网络的智能检测病毒方法[J].计算机技术与发展,2014,24(10):163.
　ZHU Li-zhi. An Intelligent Virus Detection Method Based on BP Neural Network[J].,2014,24(10):163.
[13]孙吉红[][],张丽莲[] [],武尔维[][],等. 基于智能算法的价格预测模型探究[J].计算机技术与发展,2014,24(11):107.
　SUN Ji-hong[][],ZHANG Li-lian[][],WU Er-wei[][],et al. Research on Price Prediction Model Based on Intelligent Algorithm[J].,2014,24(10):107.
[14]侯翔,廖小平. 基于PSO算法的洪水预报模型研究[J].计算机技术与发展,2015,25(04):200.
　HOU Xiang,LIAO Xiao-ping. Research on Flood Forecasting Model Based on PSO[J].,2015,25(10):200.
[15]关成立[][],杨岳[],陈兴汉[][]. 基于BP神经网络的线路板废水处理研究[J].计算机技术与发展,2015,25(08):194.
　GUAN Cheng-li[] [],YANG Yue[] CHEN Xing-han[][]. Research on Wastewater Treatment Process of Printed Circuit Board Based on Neural Network[J].,2015,25(10):194.
[16]潘春花,孙燕,朱存. 太阳黑子活动周期特征的神经网络和小波分析[J].计算机技术与发展,2016,26(03):158.
　PAN Chun-hua,SUN Yan,ZHU Cun. BP Neural Network and Wavelet Analysis of Period of Sunspot Activity[J].,2016,26(10):158.
[17]郭建峰[][],李玉[],安东[]. 基于LM遗传神经网络的短期股价预测[J].计算机技术与发展,2017,27(01):152.
　GUO Jian-feng[][],LI Yu[],AN Dong[]. Prediction for Short-term Stock Price Based on LM-GA-BP Neural Network[J].,2017,27(10):152.
[18]王栋. 基于BP神经网络的公路客运量预测方法[J].计算机技术与发展,2017,27(02):187.
　WANG Dong. Prediction Method of Highway Passenger Transportation Volume Based on BP Neural Network[J].,2017,27(10):187.

更新日期/Last Update: 2017-11-23