期刊文献+

一种功能分区的BP神经网络结构设计方法 被引量:6

Structure model of function-dividing design for BP neural network
原文传递
导出
摘要 针对全连接BP网络在解决大规模复杂问题时存在的收敛速度缓慢等问题,提出一种功能分区的BP网络结构模式.利用RBF神经元的物理特性对输入样本空间进行分解,并将分解后的样本送给不同的子BP网络学习.与全连接BP网络相比,降低了网络在学习过程中的权值搜索空间,提高了学习速度,改善了网络泛化性能,体现了人脑在学习过程中的知识积累特征.对三维墨西哥草帽函数逼近和双螺旋分类的实验结果表明,该网络能够解决全连接BP网络不能有效解决的问题. For the problem that the fully coupled BP neural network suffers the slow convergence rate to solve the large scale complex problems,a structure model of function-dividing BP neural network architecture is presented.By using the physical characteristics of the RBF neurons,the input sample space is decomposed,and different sub-samples space is sent to different sub-module of BP neural network to learn automatically.Compared with the fully coupled BP neural network,the searching space of weight in the learning process of neural network is reduced,the learning speed and network's generalization performance are improved,and the characteristics of the human brain in the learning proces of knowledge accumulation are reflected.Experiments of 3D Mexican hat function approximation and two-spiral classification show that the neural network of function-dividing BP neural network can solve the problem that the fully coupled BP neural network can not solve perfectly.
出处 《控制与决策》 EI CSCD 北大核心 2011年第11期1659-1664,共6页 Control and Decision
基金 国家自然科学基金项目(60873043) 国家"863"计划项目(2009AA04Z155) 北京市自然科学基金项目(4092010) 教育部博士点基金项目(200800050004) 北京市高等学校人才强教计划项目(PHR201006103)
关键词 BP神经网络 功能分区 权值搜索空间 知识积累 BP neural network function-dividing weight search space knowledge accumulation
  • 相关文献

参考文献12

  • 1张昭昭,乔俊飞,韩红桂.一种基于神经网络复杂度的修剪算法[J].控制与决策,2010,25(6):821-824. 被引量:10
  • 2Liu J, Feng D, Zhang W. Adaptive improved natural gradient algorithm for blind source separation[J]. Neural Computation, 2009, 21(3): 872-889.
  • 3Man Z, Wu H, Liu X. A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks[J]. IEEE Trans on Neural Networks, 2006, 17(6): 1580-1591.
  • 4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. 被引量:12
  • 5Siu S, Yang S, Lee C, et al. Improving the back-propagation algorithm using evolutionary strategy[J]. IEEE Trans on Circuits and Systems-II: Express Briefs, 2007, 54(2): 171- 175.
  • 6Zweiri Y H. Optimization of a three-term backpropagation algorithm used for neural network learning[J]. Int J ofComputational Intelligence, 2007, 3(4): 322-327.
  • 7Jianye Sun. Local coupled feedforward neural network[J]. Neural Networks, 2010, 23(1): 108-113.
  • 8Seiichi Ozawa, Asim Roy, Dmitri Roussinov. A multitask learning model for online pattern recognition[J]. IEEE Trans on Neural Networks, 2009, 20(3): 430-445.
  • 9王宪保,周德龙,王守觉.基于仿生模式识别的构造型神经网络分类方法[J].计算机学报,2007,30(12):2109-2114. 被引量:10
  • 10周志华,陈兆乾,邵栋,陈世福.一种新型自适应神经网络回归估计算法[J].计算机学报,2000,23(6):654-659. 被引量:8

二级参考文献29

共引文献35

同被引文献40

  • 1谭永红.基于BP神经网络的自适应控制[J].控制理论与应用,1994,11(1):84-88. 被引量:91
  • 2HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
  • 3HUANG G B,CHEN L.Convex incremental extreme learning machine[J].Neurocomputing,2007,70(16):3056-3062.
  • 4LAN Y,SOH Y C,HUANG G B.Two-stage extreme learningmachine for regression[J].Neurocomputing,2010,73(16):3028-3038.
  • 5SUN Z L,NG K M,SOSZYNSKA-BUDNY J,et al.Application of the LP-ELM model on transportation system lifetime optimization[J].IEEE Transactions on Intelligent Transportation Systems,2011,12(4):1484-1494.
  • 6YEU C W T,LIM M H,HUANG G B,et al.A new machine learning paradigm for terrain reconstruction[J].IEEE Geoscience and Remote Sensing Letters,2006,3(3):382-386.
  • 7TEOH E J,TAN K C,XIANG C.Estimating the number of hidden neurons in a feedforward network using the singular value decomposition[J].IEEE Transations on Neural Networks,2006,17(6):1623-1629.
  • 8HUANG G B,CHEN L,SIEW C K.Universal approximation using incremental constructive feedforward networks with random hidden nodes[J].IEEE Transations on Neural Networks,2006,17(4):879-892.
  • 9HUANG G B,CHEN L.Enhanced random search based incremental extreme learning machine[J].Neurocomputing,2008,71(16):3460-3468.
  • 10FENG G,HUANG G B,LIN Q,et al.Error minimized extreme learning machine with growth of hidden nodes and incremental learning[J].IEEE Transations on Neural Networks,2009,20(8):1352-1357.

引证文献6

二级引证文献28

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部