期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于模型输出敏感度分析的动态神经网络结构设计 被引量：11

Design of Dynamic Neural Network Based on the Sensitivity Analysis of Model Output
在线阅读 下载PDF
导出
摘要 神经网络的性能由其训练算法和拓扑结构共同确定.为了解决设计网络结构的动态调整问题,论文给出了一种神经网络结构动态设计方法.以隐含层神经元输出的贡献对模型输出敏感度进行分析,从而调整神经网络结构,对贡献太小的神经元予以删除,对贡献值太大的神经元利用最邻近法在其附近插入新的神经元.通过对非线性函数进行逼近和对非线性系统关键参数进行预测证明了该方法的有效性. The capabilities of neural networks are influenced by the learning algorithms and the topologies.Thus,in order to solve the problem of dynamic topologies,a new design method for dynamic structure of neural network is proposed in this paper.The dynamic design for neural network is based on the sensitivity analysis（SA）of the model output.This algorithm can delete the nodes in the hidden layer whose contribution ratios are too little;and add new nodes to the hidden layer whose ratios are too large relied on the the nearest neighbor interpolation.Finally,This proposed algorithm is used to track the nonlinear functions and predict the nonlinear systems,the results demonstrate the good effect of the dynamic feed-forward neural network（SAFNN）.
作者 韩红桂 李淼 乔俊飞
机构地区 北京工业大学电子信息与控制工程学院
出处 《电子学报》 EI CAS CSCD 北大核心 2010年第3期731-736,共6页 Acta Electronica Sinica
基金 国家863计划项目(No.2009AA04Z155 2007AA04Z160) 国家自然科学基金(No 60873034 60674066) 教育部博士点基金(No.200800050004) 北京市自然科学基金项目(No.4092010)
关键词 神经网络 动态结构设计 模型输出敏感度分析 neural network design of dynamic structure sensitivity analysis of model output
分类号 TP183 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献15

  • 1王小华,何怡刚.基于神经网络的FRM滤波器优化设计研究[J].电子学报,2008,36(3):486-489. 被引量：2
  • 2S S Ge, C C Hang, T H Lee, T Zhang. Stable Adaptive Neural Network Control[ M ]. Boston, MA: Kluwer, 2001.
  • 3田广,戚飞虎.移动摄像机环境下基于特征变换和SVM的分级行人检测算法[J].电子学报,2008,36(5):1024-1028. 被引量：18
  • 4Di Wang. Fast constructive-coveting algorithm for neural networks and its implement in classification [ J ]. Applied Soft Computing,2008,8( 1 ) : 166 - 173.
  • 5L Ma, K Khorasani. New training strategies for constructive neural networks with application to regression problems [ J ]. Neural Networks, 2004,17(4) :589 - 609.
  • 6Jose Manuel Cano-Izquierdo, Julio Ibarrola, Miguel Pinzolas, Miguel Almonacid. DNSP: A biologically inspired dynamic Neural network approach to signal processing [J] .Neural Networks,2008,21(7) : 1006 - 1019.
  • 7Xiaoqin Zeng,Daniel S Yeung. Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure [ J ]. Neurocomputing, 2006,69(7 - 9 ) : 825 - 837.
  • 8Liying Ma, K Khorasani. Constructive feedforward neural networks using hermite polynomial activation functions[ J]. IEEE Transaction on Neural Networks, 2005,16(4):821 -833.
  • 9P L Narasimha, W H Delashmit, Michael T Manry, Jiang Li, F Maldonado. An integrated growing-pruning method for feedforward network training [J]. Neurocomputing, 2008, 71 ( 13 - 15) :2831 - 2847.
  • 10Guang-Bin Huang, P Saratchandran, Narasimhan Sundararajan. A generalized growing and prtming RBF (GGAP-RBF) neural network for function approximation[ J]. IEEE Transaction on Neural Networks, 2005, 16( 1 ) :57 - 67.

二级参考文献26

  • 1杜友田,陈峰,徐文立,李永彬.基于视觉的人的运动识别综述[J].电子学报,2007,35(1):84-90. 被引量：80
  • 2Lim Y C. Frequency-response-masking approach for the synthesis of sharp linear phase digital filters[J]. IEEE, Trans, 1986, CAS-33(4) :357 - 364.
  • 3Lim Y C, Lian Y. The optimum design of one-and two- dimensional FIR filters using the frequency response masking technique[ J ]. IEEE Trans, 1993, CASII-40(2) : 88 - 95.
  • 4Barcellos L C, Netto S L, Diniz S R. Design of FIR filters combining the frequency-response-masking and the WLS Chebyshev approach[A]. Barcellos L C Proc IEEE Int Syinp Circuits Syst[C]. New Jersey: IEEE Press, 2001.613 - 616.
  • 5Lim Y C, Lian Y. Frequency-response-masking approach for digital filter design: Complexity reduction via masking filters factorization[ J ]. IEEE Trans, 1994, CASII-41 ( 8 ) : 518 - 525.
  • 6Saramaki T, Lim Y C. Use of Remez algorithm for designing FIR filters utilizing the frequency-response- masking approach [A]. Saramaki T. Proc IEEE Int Symp Circuits Syst[C]. New Jersey: IEEE Press, 1999.449 - 455.
  • 7Lian Y, Zhang L, Ko C C. An improve frequency response masking approach for designing sharp FIR filters [ J]. Signal Processing, 2001,81 (12) : 2573 - 2581.
  • 8Lee W R, Rehbock V,Teo K L, et al.A weight-least-squarebased approach to FIR filter design using the frequency response masking technique [J]. IEEE Signal Processing Letters, 2004,11(7) :593 - 596.
  • 9Lu W S, Hinamoto T. Optimal design of frequency-responsemasking filters using semidefinite programming [ J ]. IEEE Trans, 2003, CASI-50(4) : 557 - 568.
  • 10C Demirkir, B Sankur.Face detection using look-up table based gentle adaBoost[A]. Lecture Notes in Computer Science 3546- Audio-and Video-based Biometric Person Authentication (AVBPA2005) [ C ]. Berlin: Springer-Verlag, 2005.339 - 345.

共引文献18

同被引文献112

引证文献11

二级引证文献43

电子学报
2010年 第3期

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