首页 | 本学科首页   官方微博 | 高级检索  
     

改进的粒子群动态过程神经网络及其应用
引用本文:于广滨,李瑰贤,金向阳,白彦伟. 改进的粒子群动态过程神经网络及其应用[J]. 吉林大学学报(工学版), 2008, 38(5): 1141-1145
作者姓名:于广滨  李瑰贤  金向阳  白彦伟
作者单位:哈尔滨工业大学,机电工程学院,哈尔滨,150001;哈尔滨工业大学,机电工程学院,哈尔滨,150001;哈尔滨商业大学,轻工学院,哈尔滨,150028
基金项目:黑龙江省国际科技合作项目,高等学校学科创新引智计划项目
摘    要:为克服前向过程神经网络收敛速度慢、精度低的问题,本文提出了一种基于改进的粒子群动态过程神经网络(IDPNN)。对于给定的全连接的过程神经网络,通过IPSO优化其连接权值和网络结构删除冗余连接使之成为部分连接的过程神经网络系统,从而降低了计算成本。将经过IPSO训练的动态过程神经网络应用于Iris模式分类问题,结果表明,改进的粒子群动态过程神经网络具有较高的收敛速度和精确性。

关 键 词:人工智能  动态过程神经网络  粒子群算法  模式分类
收稿时间:2007-04-02

Modified particle swarm dynamic process neural network and its application
YU Guang-bin,LI Gui-xian,JIN Xiang-yang,BAI Yan-wei. Modified particle swarm dynamic process neural network and its application[J]. Journal of Jilin University:Eng and Technol Ed, 2008, 38(5): 1141-1145
Authors:YU Guang-bin  LI Gui-xian  JIN Xiang-yang  BAI Yan-wei
Affiliation:1.School of Mechanical and Electrical Engineering;Harbin Institute of Technology;Harbin 150001;China;2.College of Light Industry;Harbin University of Commerce;Harbin 150028;China
Abstract:To overcome the shortcomings of slow convergent speed and low accuracy of the feedforward process neural network, an Improved Particle Swarm Optimization (IPSO) is proposed to train the dynamic process neural network. A fully connected feedforward dynamic process neural network can be converted into partially connected network by tuning the structure and choosing the connection weights of PNN simultaneously. This will result in significant cost reduction in implementation of the neural network. The dynamic process neural network trained by IPSO has been applied to Iris pattern classification. Results show that the modified particle swarm dynamic process neural network can accelerate the convergent speed and improve the accuracy.
Keywords:artificial intelligence  improved dynamic process neural network(IDPNN)  particle swarm optimization  pattern classification
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《吉林大学学报(工学版)》浏览原始摘要信息
点击此处可从《吉林大学学报(工学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号