期刊文献+

一种用于方向预测的集成学习算法 被引量:2

An Ensemble Learning Algorithm for Direction Prediction
下载PDF
导出
摘要 对用方向向量标识示例的学习问题,以预测方向与实际方向之间的方向误差最小化为目标,提出了一种可用于方向预测的集成学习算法,详细分析了构造多个预测函数以及组合各个预测函数以实现方向的最优化预测方法.提出的算法具有广泛的应用特性:当用不同的轴向来标识类别时,可简化得到多分类连续AdaBoost算法,其能确保训练错误率随分类器个数增加而降低;用错分代价组成的向量来标识示例时,可简化得到一种平均错分代价最小化的集成学习算法.理论分析和实验结果均表明了算法的合理性和有效性. To resolve the learning problem in which the instances are labeled by vectors,with the destination of direction error minimization between the direction represented by prediction vector and the direction represented by actual vector,an ensemble learning algorithm for direction prediction was proposed.The methods to construct multiple prediction functions and to combine them to realize the optimized prediction of instance directions were put forward.This algorithm is very general.When the different classes are labeled by the different direction vectors of axes,the proposed algorithm is degenerated to real AdaBoost algorithm for multi-class classification,guaranteeing that the training error of the combination classifier can be reduced while the number of trained classifiers increases.When the instances are labeled by the vector composed of the classification costs of all classes,the proposed algorithm is degenerated to an ensemble learning algorithm for cost-sensitive classification which can minimize average classification cost.The theoretical analysis and experimental results show that the proposed algorithm is reasonable and effective.
作者 付忠良
出处 《上海交通大学学报》 EI CAS CSCD 北大核心 2012年第2期250-258,共9页 Journal of Shanghai Jiaotong University
基金 四川省科技支撑计划项目(2008SZ0100 2009SZ0214)
关键词 结构化预测 方向预测 模糊分类 代价敏感 ADABOOST算法 structured prediction direction prediction fuzzy classification cost-sensitive AdaBoost algorithm
  • 引文网络
  • 相关文献

参考文献17

  • 1Lafferty J,McCallum A,Pereira F.Conditional ran-dom fields:Probabilistic models for segmenting andlabeling sequence data[C] //Proc of the InternationalConf on Machine Learning.San Mateo:MorganKaufmann,2001:282-289. 被引量:1
  • 2Taskar B,Guestrin C,Koller D.Max-margin Mark-ov networks[C] //Advances in Neural InformationProcessing Systems16.Cambridge:MIT,2004:25-32. 被引量:1
  • 3Tsochantaridis I,Hofmann T,Joachims T,et al.Support vector machine learning for interdependentand structured output spaces[C] //Proc of the Inter-national Conf on Machine Learning.Menlo Park:AAAI,2004:1-8. 被引量:1
  • 4叶少珍,张钹,吴鸣锐,郑文波.一种基于神经网络覆盖构造法的模糊分类器[J].软件学报,2003,14(3):429-434. 被引量:18
  • 5阳爱民..模糊分类模型的研究[D].复旦大学,2005:
  • 6Freund Y,Schapire R E.A decision-theoretic gener-alization of on-line learning and an application toboosting[J].Journal of Computer and System Sci-ences,1997,55(1):119-139. 被引量:1
  • 7Schapire R E,Singer Y.Improved boosting algo-rithms using confidence-rated predictions[J].Ma-chine Learning,1999,37(3):297-336. 被引量:1
  • 8Zhu J,Rosset S,Zou H,et al.Multi-class AdaBoost[J].Statistics and Its Interface,2009(2):349-360. 被引量:1
  • 9付忠良.分类器线性组合的有效性和最佳组合问题的研究[J].计算机研究与发展,2009,46(7):1206-1216. 被引量:29
  • 10Boutell M R,Luo J,Shen X P,et al.Learningmulti-label scene classification[J].Pattern Recogni-tion,2004,37:1757-1771. 被引量:1

二级参考文献58

  • 1燕继坤,郑辉,王艳,曾立君.基于可信度的投票法[J].计算机学报,2005,28(8):1308-1313. 被引量:8
  • 2武勃,黄畅,艾海舟,劳世竑.基于连续Adaboost算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621. 被引量:66
  • 3Valiant L G.A theory of the learnable[J].Communications of the ACM,1984,27(11):1134-1142. 被引量:1
  • 4Schapire R E.The strength of weak learnability[J].Machine Learning,1990,5(2):197-227. 被引量:1
  • 5Freund Y,Schapire R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139. 被引量:1
  • 6Breirnan L.Bagging predicators[J].Machine Learning,1996,24(2):123-140. 被引量:1
  • 7Xu L,Krzyzak A,Suen C Y.Methods of combining multiple classifiers and their application to handwriting recognition[J].IEEE Trans on System,Man,and Cybernetics,1992,22(3):418-435. 被引量:1
  • 8Perrone M P.Improving regression estimationn:Averaging methods for variance reduction with extensions to general convex measure optimization[D].Rhode Island,USA:Brown University,Department of Physics,1993. 被引量:1
  • 9Fumera G,Roil F.A theoretical and experimental analysis of linear combiners for multiple classifier systems[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(6):942-956. 被引量:1
  • 10Kittler J,Hater M,Duin R,et al.On combining classifiers[J].IEEE Trans on Pattern Analysis and Machine Intelligence.1998,20(3):226-234. 被引量:1

共引文献139

同被引文献10

引证文献2

二级引证文献23

;
使用帮助 返回顶部