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Madaline网络敏感性的主动学习算法研究

An active learning algorithm based on sensitivity of Madaline network
在线阅读 下载PDF
导出
摘要 提出一种基于Madaline网络敏感性的主动学习算法。首先用部分样本训练Madaline网络,然后以Madaline网络输出对其输入在给定样本点附近变化的敏感性为尺度,主动从未参与训练的样本中挑选敏感性相对大的样本继续进行训练,循环反复这个过程直到满足训练要求为止。实验验证了该主动学习算法处理离散分类问题的有效性和可行性。 This paper presents an active learning algorithm based on the Madaline network＇s output sensitivity due to its input variation near a given sample. First, a portion of samples are used to train a Madaline network. Then, based on the sensitivity of the network, some other samples with higher sensitivity are actively selected and added into the training data to continue the training of the network. This process is repeated until the training requirement is met. Experiments verified the effectiveness and feasibility of the proposed active learning algorithm in treating discrete classification problems.
作者 曾晓勤 赵倩倩 何嘉晟
机构地区 河海大学计算机与信息学院
出处 《河海大学学报（自然科学版）》 CAS CSCD 北大核心 2014年第3期278-282,共5页 Journal of Hohai University(Natural Sciences)
基金 国家自然科学基金(60971088)
关键词 Madaline网络 网络敏感性 主动学习 Madaline network network sensitivity active learning
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14

  • 1FREUND Y,SEUNG H S,SHAMIR E,et al.Selective sampling using the query by committee algorithm[ J ].Machine Learning,1997,28(2/3):133-168.
  • 2DAGON I,ENGELSON S.Committee-based sample selection for probabilistic classifiers [ C ]//Proceedings of 12th Int'l Confon Machine Learning.San Francisco,CA:Morgan Kaufmann,1995:150-157.
  • 3ARGAMON-ENGLESON S,DAGAN I.Committee-based sample selection for probabilistic classifiers [ J ].Journal of Artificial Intelligence Research,1999:11:335-360.
  • 4LEWIS D D,GAIL W A.A sequential algorithm for training text classifiers:corrigendum and additional data [ J ].Sigir Forum,1995,29(2):13-19.
  • 5MCCALLUM A K,NIGAM K.Employing EM and pool-based active learning for text classification [ C]//Proceedings of the Fifteenth International Conference.Madison,WI,USA:Morgan Kaufmann Publishers,1998:350-358.
  • 6MUSLEA I,MINTON S,KNOBLOCK C A.Active learning with multiple view [ J ].Journal of Artificial Intelligence Research,2006,27:203-233.
  • 7RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back propagation errors[ J].Nature,1986,323:533-536.
  • 8RUMELHART D E,MCCLELLAND J L.Parallel distributed processing:explorations in the microstrncture of eognition,vol.1 [ M ].Cambridge:MIT Press,1986.
  • 9WINTER R,WIDROW B.Madaline rule I1:a training algorithm for neural networks [ C ]//IEEE International Conference on Neural Networks.San Diega,CA,USA:IEEE Publishrs,1988:401-408.
  • 10WINTER R.Madaline rule 1/:a new method for training networks for Adalines [ D].Stanford:Standford University,1989.

二级参考文献26

  • 1FU L, CHEN T. Sensitivity analysis for input vector in multilayer feedforward neural networks[ C]//Proc of IEEE International Conference on Neural Networks. San Francisco,CA:IEEE Press, 1993:215-218.
  • 2YEUNG D S, SUN Xuequan. Using function approximation to analyze the sensitivity of the MLP with antisymmetric squashing activation function[ J]. IEEE Transactions on Neural Networks, 2002,13 ( 1 ) : 34-44.
  • 3ZENG Xiaoqin, YEUNG D S. Sensitivity analysis of multilayer perceptron to input and weight perturbations [ J]- IEEE Transactions on Neural Networks, 2001, 12(6): 1358-1366.
  • 4ZENG Xiaoqin, YEUNG D S. A quantified sensitivity measure for muhilayer perceptron to input perturbation [ J ]. Neural Computation, 2003, 15(1 ): 183-212.
  • 5YANG Jing, ZENG Xiaoqin, ZHONG Shuiming. Computation of mulitilayer perceptron sensitivity to input perturbation [ J ]. Neurocomputing, 2013, 99( 1 ) : 390-398.
  • 6YANG S, HO C, SIU S. Sensitivity analysis of the split-complex valued multilayer perceptron due to the Inputs and Weights[ J ]. IEEE Trans on Neural Networks, 2007, 18 (5) : 1280-1293.
  • 7BERNIER J L, ORTEGA J, ROJAS I, et al. Improving the tolerance of Multilayer Perceptrons by minimizing the statistical sensitivity to weight deviations [ J ]. Neurocomputing, 2000, 31 ( 1 ) : 87-103.
  • 8BERNIER J L, ORTEGA J, ROS E, et al. A quantitative study of fault tolerance,noise immunity and generalization ability of MLPs[J]. Neural Computation, 2000, 12(12) :2941-2964.
  • 9ENGELBRECHT A P. A new pruning heuristic based on variance analysis of sensitivity information[ J ]. IEEE Transactions on Neural Networks, 2001, 12 (6) : 1386-1399.
  • 10ZENG Xiaoqin, YEUNG D S. Hidden neuron pruning of muhilayer perceptrons using a quantified sensitivity measure [ J]. Neurocomputing, 2006, 69 (7/8/9) : 825-837.

共引文献2

河海大学学报（自然科学版）
2014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