[1]薄迎春,乔俊飞,杨刚.一种多模块协同参与的神经网络[J].智能系统学报,2011,6(03):225-230.
 BO Yingchun,QIAO Junfei,YANG Gang.A multimodule cooperative neural network[J].CAAI Transactions on Intelligent Systems,2011,6(03):225-230.
点击复制

一种多模块协同参与的神经网络(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第6卷
期数:
2011年03期
页码:
225-230
栏目:
出版日期:
2011-06-25

文章信息/Info

Title:
A multimodule cooperative neural network
文章编号:
1673-4785(2011)03-0225-06
作者:
薄迎春乔俊飞杨刚
北京工业大学 电子信息与控制工程学院,北京 100124
Author(s):
BO Yingchun QIAO Junfei YANG Gang 
College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
关键词:
神经网络条件模糊聚类多模块子网络选择
Keywords:
neural networks conditional fuzzy clustering method multimodules subnets selection
分类号:
TP183
文献标志码:
A
摘要:
针对单一神经网络训练时间长、对复杂问题处理精度较低、易陷入局部极小等问题,提出了一种多模块协同参与信息处理的神经网络.该神经网络具有层级结构,基于条件模糊聚类技术对样本进行分类,根据分类结果实现对神经网络的模块划分,采用代数算法对网络权值进行求解,基于距离测度设计了处理输入信息的子网络选择方法.为提高神经网络对复杂问题的逼近能力,选择数目不等的多个子网络参与给定输入的协同处理,采取“分而治之”与“集成学习”相结合方法以提高网络的性能.实验表明,对于复杂问题,这种多模块协同参与的神经网络可以有效地提高网络的逼近精度,训练时间也优于单一网络.
Abstract:
Aiming to solve the problems of long training time, low precision in processing complex problem, and a local minimum in single neural networks, a multimodule cooperative neural network (MMCNN) was proposed. Its structure has hierarchical character. Sample data was first detached by the fuzzy clustering method, and then the neural network was partitioned into several subnets based on the clustering results. The linking weights were elicited by solving equations. For a given input data, some multimodules were selected to deal with it. The approximating performance was improved by combining divideandconquer and learning ensemble strategies. A subnet selection method was designed based on distance measurements. Simulation results demonstrate that a multimodule cooperative neural network can heighten approximating ability effectively for complicated problems, and the training time is faster than in a single backpropagation neural network.

参考文献/References:

[1]GARPENTER G A. Largescale neural systems for vision and cognition[C]//Proceedings of International Joint Conference on Neural Networks.Boston, USA, 2009: 1419.
[2]JACOBS R A, JORDAN M I. A modular connectionist architecture for learning piecewise control strategies[C]//Proceedings of the American Control Conference. Boston, USA, 1991: 343351.
[3]PEDRYCZ W, VUKVICH G. Granular neural networks [J]. Neurocomputing, 2001(36): 205224.
[4]DATER M A, GORDON V S. Vehicle steering control using modular neural networks[C]//IEEE International Conference on Information Reuse and Integration. Las Vegas, USA, 2005: 374379.
[5]SANTOS J M, ALEXANDRE L A, De SA J M. Modular neural network task decomposition via entropic clustering[C]//Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications. Porto, Portugal, 2006: 16.
[6]PARK H S, PEDRYCZ W. Granular neural networks and their development through contextbased clustering and adjustable dimensionality of receptive fields[J]. IEEE Transactions on Neural Networks, 2009, 20(10): 16041616.
[7]CIMINO M G C A, PEDRYCZ W, LAZZERINI B, et al. Using multilayer perceptrons as receptive fields in the design of neural networks[J]. Neurocomputing, 2009, 72(10/11/12): 25362548.
[8]GOH H L, LIM J H, QUEK C. Learning from an ensemble of receptive fields[C]//Proceedings of the 8th IEEE International Conference on Cognitive Informatics (ICCI). Hong Kong, China, 2009: 8693.
[9]PEDRYCZ W. Conditional fuzzy clustering in the design of radial basis function neural networks[J]. IEEE Transactions on Neural Networks, 1998, 4(9): 601612.
[10]王攀,李幼凤,范衠,等.模块化神经网络子网的动态集成方法学研究[J].系统工程与电子技术, 2008, 30(6): 11431147.
WANG Pan, LI Youfeng, FAN Zhun, et al. Methodological research for dynamic integration of modular neural network’s subnetworks[J]. Systems Engineering and Electronics, 2008, 30(6): 11431147.
[11]WANG Shuning, HUANG Xiaolin, JUNAID K M. Configuration of continuous piecewiselinear neural networks[J]. IEEE Transactions on Neural Networks, 2008, 19(8): 14311444.
[12]WEDGE D, INGRAM D, MCLEAN D, et al. On globallocal artificial neural networks for function approximation[J].IEEE Transactions on Neural Networks, 2006, 17(4): 942952.
[13]乔俊飞,张颖.一种多层前馈神经网络的快速修剪算法[J].智能系统学报, 2008, 3(2): 173176.
QIAO Junfei, ZHANG Ying. Fast unit pruning algorithm for multilayer feedforward network design[J]. CAAI Transactions on Intelligent Systems, 2008, 3(2): 173176.

相似文献/References:

[1]丁永生.计算智能的新框架:生物网络结构[J].智能系统学报,2007,2(02):26.
 DING Yong-sheng.A new scheme for computational intelligence: bio-network architecture[J].CAAI Transactions on Intelligent Systems,2007,2(03):26.
[2]徐 雄.人工情感的进化控制系统实现[J].智能系统学报,2008,3(02):135.
 XU Xiong.Implementation of an evolutionary control system based on artificial emotion[J].CAAI Transactions on Intelligent Systems,2008,3(03):135.
[3]周孔丹,李 宁,鲁华祥.单电子电路的鲁棒性研究[J].智能系统学报,2008,3(03):195.
 ZHOU Kong-dan,LI Ning,LU Hua-xiang.Researching the robustness of single electron devices[J].CAAI Transactions on Intelligent Systems,2008,3(03):195.
[4]张米娜,韩红桂,乔俊飞.前馈神经网络结构动态增长-修剪方法[J].智能系统学报,2011,6(02):101.
 ZHANG Mina,HAN Honggui,QIAO Junfei.Research on dynamic feedforward neural network structure based on growing and pruning methods[J].CAAI Transactions on Intelligent Systems,2011,6(03):101.
[5]张文辉,高九州,马静,等.漂浮基空间机器人的径向基神经网络鲁棒自适应控制[J].智能系统学报,2011,6(02):114.
 ZHANG Wenhui,GAO Jiuzhou,MA Jing,et al.The RBF neural network robust adaptive control of a freefloating space robot[J].CAAI Transactions on Intelligent Systems,2011,6(03):114.
[6]蒲兴成,张军,张毅.基于神经网络的改进行为协调控制及其在智能轮椅路径规划中的应用[J].智能系统学报,2011,6(05):456.
 PU Xingcheng,ZHANG Jun,ZHANG Yi.Modified behavior coordination for intelligent wheelchair path planning based on a neural network[J].CAAI Transactions on Intelligent Systems,2011,6(03):456.
[7]段海庆,朱齐丹.基于反步自适应神经网络的船舶航迹控制[J].智能系统学报,2012,7(03):259.
 DUAN Haiqing,ZHU Qidan.Trajectory tracking control of ships based onan adaptive backstepping neural network[J].CAAI Transactions on Intelligent Systems,2012,7(03):259.
[8]乔俊飞,逄泽芳,韩红桂.基于改进粒子群算法的污水处理过程神经网络优化控制[J].智能系统学报,2012,7(05):429.
 QIAO Junfei,PANG Zefang,HAN Honggui.Neural network optimal control for wastewater treatment processbased on APSO[J].CAAI Transactions on Intelligent Systems,2012,7(03):429.
[9]郭一,刘金琨.带执行器饱和的柔性关节机器人位置反馈动态面控制[J].智能系统学报,2013,8(01):21.[doi:10.3969/j.issn.1673-4785.201204012]
 GUO Yi,LIU Jinkun.Position feedback dynamic surface control for flexible joint robots with actuator saturation[J].CAAI Transactions on Intelligent Systems,2013,8(03):21.[doi:10.3969/j.issn.1673-4785.201204012]
[10]拓守恒.一种优化神经网络的教与学优化算法[J].智能系统学报,2013,8(04):327.[doi:10.3969/j.issn.1673-4785.201305026]
 TUO Shouheng.A modified teaching-learning-based optimization algorithm and application in neural networks[J].CAAI Transactions on Intelligent Systems,2013,8(03):327.[doi:10.3969/j.issn.1673-4785.201305026]

备注/Memo

备注/Memo:
收稿日期:2010-04-07.
基金项目:国家自然科学基金资助项目(60873043);北京市自然科学基金资助项目(4092010);教育部博士点基金资助项目(200800050004);北京市属高等学校人才强教计划资助项目(PHR201006103).
通信作者:薄迎春.E-mail:boyingchun@sina.com.
作者简介:
薄迎春,男,1977年生,博士研究生,讲师,主要研究方向为神经计算与智能优化控制.
乔俊飞,男,1968年生,教授,博士生导师,博士,中国人工智能学会理事、科普工作委员会秘书长,中国自动化学会智能专业委员会委员,北京自动化学会常务理事,北京人工智能学会理事、秘书长.主要研究方向为复杂过程建模与控制、神经计算与智能优化控制.主持多项国家“863”计划项目,发表学术论文多篇,被SCI、EI检索50余篇. 
杨刚,男,1983年生,博士研究生,主要研究方向为神经计算与智能优化控制.
更新日期/Last Update: 2011-07-23