跳到主要內容

臺灣博碩士論文加值系統

(54.161.24.9) 您好!臺灣時間:2022/01/17 12:23
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:許哲銘
研究生(外文):Jer-Ming Hsu
論文名稱:不完整資料學習演算法使用支援向量機器
論文名稱(外文):Learning from Incomplete Data using Support Vector Machines
指導教授:胡毓志
指導教授(外文):Yuh-Jyh Hu
學位類別:碩士
校院名稱:國立交通大學
系所名稱:資訊科學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:英文
論文頁數:54
中文關鍵詞:不完整資料支援向量機器分類學習演算法
外文關鍵詞:missing dataincomplete datasupport vector machinesEMmixture modelclassification
相關次數:
  • 被引用被引用:1
  • 點閱點閱:574
  • 評分評分:
  • 下載下載:143
  • 收藏至我的研究室書目清單書目收藏:2
在實務上,學習工作經常得處理的高維度的資料,而且部分資料甚至是不完整的。一般的方法處理不完整的資料只是簡單地將遺失的部分填上平均值,這樣通常得不到理想的結果。而最近這幾年,支援向量機器(SVMs)在分類和回歸分析上的問題往往有相當不錯的表現,可是目前只能處理完整的資料,因此,我們改良支援向量機器的演算法,賦予它在訓練和預測階段有處理不完整的資料的能力。我們的方法首先需要資料的機率分佈來加權不完整的資料比重,而機率分佈則採用混合的模型,我們採用期望值最大化(EM)演算法來估量該機率分佈的參數。針對高斯混合模型,我們的SVMs採用radial basis kernel可以得到簡單和快速的計算方式。如果採用其他的機率模型或其他的kernel,我們依然可以採用蒙地卡羅法來得到結果。在我們的實驗裡,我們的方法得到比填入期望值和條件期望值來得更好的結果。
Real-world learning tasks often involve high-dimensional data sets with complex patterns of incomplete data. Conventional techniques to deal with missing data are simply to fill with means. In practice, it often fails to obtain satisfactory results. In recently years, support vector machines (SVMs) on various classification and regression problems usually have excellent performance. Thus, we analyze how incomplete data can be incorporated into the training and recalling of SVMs. In our approach, we need the data density to weight the incomplete data. We apply the expectation-maximization (EM) algorithm to estimate the parameters of the data density based on mixture modeling. For Gaussian mixtures model, the closed-form solution of SVMs with Gaussian radial basis kernel is derived. For other densities and kernel functions, the solution can be evaluated by Monte Carlo integration techniques. In our experimental results, we have obtained favorable results in comparison to unconditional mean imputation and conditional mean imputation.
Chapter 1. Introduction
Chapter 2. The EM Algorithms
Chapter 3. Support Vector Machines
Chapter 4. Missing Support Vector Machines
Chapter 5. Experimental Results
Chapter 6. Conclusion
Bibliography
\bibitem{Ahmad93} {\small Ahmad, S. and Tresp, V., ''Some Solutions to the
Missing Feature Problem in Vision,'''' \textit{Advances in Neural Information
Processing System 5}, The MIT Press, 1993. }
\bibitem{Anderson57} {\small Anderson, T.W., ''\textit{An Introduction to
Multivariate Statistical Analysis},'''' Stanford, 1957. }
\bibitem{Bazaraa93} {\small Bazaraa, M. S., Sherali, H. D., and Shetty, C.
M., ''\textit{Nonlinear Programming: theory and algorithms,}'''' John Wiley \&
Sons, 1993. }
\bibitem{Bickel01} {\small Bickel, P. J. and Doksum, K. A., ''\textit{%
Mathematical Statistics,}'''' Prentice Hall, 2001. }
\bibitem{Bilmes98} {\small Bilmes, J. A., ''A Gentle Tutorial of the EM
Algorithm and its Application to Parameter Estimation for Gaussian Mixture
and Hidden Markov Models,'''' \textit{Technical Report, University of
Berkeley, ICSI-TR-97-021}, 1997. }
\bibitem{Burges98} {\small Burges, C. J. C., ''A Tutorial on Support Vector
Machines for Pattern Recognition,'''' \textit{Data Mining and Knowledge
Discovery}, 2, pages 121-167, 1998. }
\bibitem{Campbell} {\small Campbell, C., ''Kernel Methods: A Survey of
Current Techniques,'''' \textit{tutorial submission to a journal Special Issue}
.}
\bibitem{Casella01} {\small Casella, G. and Berger, R. L., ''\textit{%
Statistical Inference,}'''' Duxbury, 2001. }
\bibitem{Cooke00} {\small Cooke M.P., Green, P.D., Josifovski, L. and
Vizinho, A., ''Robust Automatic Speech Recognition with Missing and
Unreliable Acoustic Data'''', \textit{Speech Communication}, 2000. }
\bibitem{Cristianini00} {\small Cristianini, N. and Taylor, J. S., ''%
\textit{An Introduction to Support Vector Machines: and other kernel-based
learning methods,}'''' Cambridge University Press, 2000. }
\bibitem{Dempster77} {\small Dempster, A. P., Laird, N. M., and Rubin, D.
B., ''Maximum-likelihood from Incomplete Data via the EM algorithm\textit{,}%
'''' \textit{Journal of Royal Statistical Society Serial B}, 39, pages1--38,
1977. }
\bibitem{Gelman95} {\small Gelman, A., \textit{et. al.}, ''\textit{Bayesian
Data Analysis,}'''' Chapman \& Hall, 1995. }
\bibitem{Ghahramani94} {\small Ghahramani, Z. and Jordan, M. I.,
''Supervised Learning from Incomplete Data via an EM approach,'''' \textit{%
Advances in Neural Information Processing System 6,} The MIT Press, 1994. }
\bibitem{Ghahramani95} {\small Ghahramani, Z. and Jordan, M. I., ''Learning
from Incomplete Data,'''' \textit{Technical Report AI Lab Memo No. 1509, CBCL
Paper No. 108, }MIT AI Lab, August 1995. }
\bibitem{Green01} {\small Green, P.D., Barker, J., Cooke M.P., and
Josifovski, L., ''Handling Missing and Unreliable Information in Speech
Recognition'''', \textit{Proceedings of the Eighth International Workshop on
Artificial Intelligence and Statistics}, 2001. }
\bibitem{Hastings70} {\small Hastings, W. K., ''Monte Carlo Sampling
Methods using Markov Chains and their Applications\textit{,}'''' \textit{%
Biometrika}, 57, pages 97--109, 1970. }
\bibitem{Haykin99} {\small Haykin, S., ''\textit{Neural Networks: a
comprehensive foundation,}'''' Prentice Hall, 1999. }
\bibitem{Jaakkola98} {\small Jaakkola, T., Diekhans, M., and Haussler, D.,
''A Discriminative Framework for Detecting Remote Protein Homologies,''''
unpublished, available from \textit{%
http://www.cse.ucsc.edu/research/compbio/research.html}, 1998. }
\bibitem{Jaakkola99} {\small Jaakkola, T. and Haussler, D. ''Exploiting
Generative Models in Discriminative Classifiers,'''' \textit{Advances in
Neural Information Processing System 11}, The MIT Press, 1999. }
\bibitem{Jaakkola992} {\small Jaakkola, T. and Haussler, D.,
''Probabilistic kernel regression models,'''' \textit{Proceedings of the
Seventh International Workshop on Artificial Intelligence and Statistics},
1999. }
\bibitem{LIBSVM} {\small Chang, C.-C. and Lin, C.-J., ''LIBSVM: a library
for support vector machines,'''' Software available a \textit{%
http://www.csie.ntu.edu.tw/\symbol{126}cjlin/libsvm}, 2001. }
\bibitem{Lee99} {\small Lee, Y. J. and Mangasarian, O. L., ''SSVM: Smooth
Support Vector Machine for Classification,'''' \textit{Data Mining Institute
Technical Report 99-03, Computational Optimization and Applications},
September 1999. }
\bibitem{Little87} {\small Little, R. J. A. and Rubin, D. B., ''\textit{%
Statistical Analysis with Missing Data\/''''}, John Wiley \& Sons, 1987. }
\bibitem{Liu95} {\small Liu, C. H. and Rubin, D. B., ''ML Estimation of the
$t$ Distribution using EM and its extensions, ECM and ECME,'''' \textit{%
Statistica Sinica 5}, pages 19-39, 1995. }
\bibitem{McLanchlan97} {\small McLachlan, G. J. and Krishnan, T., ''\textit{%
The EM Algorithm and Extensions,}'''' John Wiley \& Sons, 1997. }
\bibitem{McLachlan00} {\small McLachlan, G. and Peel, D., ''\textit{Finite
Mixture Models},'''' John Wiley \& Sons, 2000. }
\bibitem{McLanchlan02} {\small McLachlan, G. J., Bean, R. W., and Peel, D.,
''A Mixture Model-based Approach to the Clustering of Microarray Expression
Data,'''' \textit{Bioinformatics}, 2002. }
\bibitem{Meng91} {\small Meng, X. L. and Rubin, D. B., ''Using EM to Obtain
Asymptotic Variance-Covariance Matrices: The SEM Algorithm,'''' \textit{the
Journal of the American Statistical Association}, 86, pages 899-909, 1991. }
\bibitem{Meng97} {\small Meng, X. L. and van Dyk, D., ''The EM
Algorithm--an old folk song sung to a fast new tune(with discussion),''''
\textit{Journal of Royal Statistical Society Serial B}, 59, pages511--567,
1997. }
\bibitem{Mitchell97} {\small Mitchell, T. M., ''\textit{Machine Learing,}''''
McGraw-Hill, 1997. }
\bibitem{Nash95} {\small Nash, S. G. and Sofer., A., ''\textit{Linear and
Nonlinear Programming,}'''' McGraw-Hill, 1995. }
\bibitem{Peel00} {\small Peel, D. and McLachlan, G. J., ''Robust Mixture
Modeling using the $t$ Distribtuion,'''' \textit{Statistics and Computing},
10, 2000. }
\bibitem{Recipes92} {\small Press, W. H., \textit{et. al.}, ''\textit{%
Numerical Recipes in C: the art of scientific computing,}'''' Cambridge
University Press, 1992. }
\bibitem{Ross97} {\small Ross, S. M., ''\textit{Simulation,}'''' Academic
Press, 1997. }
\bibitem{Rubin87} {\small Rubin, D. B., ''\textit{Multiple Imputation for
Nonresponse in Surveys},'''' John Wiley \& Sons, 1987. }
\bibitem{Schafer94} {\small Schafer, J. ''\textit{Analysis of Incomplete
for Nonresponse in Surveys},'''' Chapman \& Hall, London, 1994. }
\bibitem{Scholkopf99} {\small Scholkopf, B. and Burges, C. J.C., ''\textit{%
Advances in Kernel Methods: support vector learning,}'''' The MIT Press, 1999.
}
\bibitem{Schott97} {\small Schott, J. R., ''\textit{Matrix Analysis for
Statistics},'''' John Wiley \& Sons, 1997 }
\bibitem{Smith01} {\small Smith, N., Gales, M., and Niranjan, M.,
''Data-dependent Kernels in SVM Classification of Speech Patterns,'''' \textit{%
Technical Report, Cambridge University Engineering Dept., TR.387}, 2001. }
\bibitem{Smola00} {\small Smola, A. J., \textit{et al}., ''\textit{Advancs
in Large Margin Classifiers,}'''' The MIT Press, 2000. }
\bibitem{Sollich00} {\small Sollich, P. ''Probabilistic Methods for Support
Vector Machines,'''' \textit{Advances in Neural Information Processing System}%
, The MIT Press, 2000. }
\bibitem{Solich99} {\small Sollich, P., ''Probabilistic Interpretation and
Bayesian Methods for Support Vector Machines,'''' \textit{International
Conference on Artificial Neural Networks}, 1999. }
\bibitem{Tresp93} {\small Tresp, V., Ahmad, S., and Neuneier, R.,
''Uncertainty in the Inputs of Neural Networks,'''' \textit{Neural Network for
Computing}, 1993. }
\bibitem{Tresp94} {\small Tresp, V., Ahmad, S. and Neuneier, R., ''Training
Neural Networks with Deficient Data,'''' \textit{Advances in Neural
Information Processing System 6}, The MIT Press, 1994. }
\bibitem{Tresp95} {\small Tresp, V., Neuneier, R., and Ahmad, S.,
''Efficient Methods for Dealing with Missing Data in Supervised Learning,''''
\textit{Advances in Neural Information Processing System 7}, The MIT Press,
1995. }
\bibitem{Tresp95Prob} {\small Tresp, V., Hollatz, J. and Ahmad, S.,
''Representing Probabilistic Rules with Networks of Gaussian Basis
Functions,'''' \textit{Machine Learning}, 1995. }
\bibitem{Tsuda02} {\small Tsuda, K., Kawanabe, M., Ratsch, G., Sonnenburg
S., and Muller, K.-R., ''A New Discriminative Kernel From Probabilistic
Models'''', \textit{Advances in Neural Information Processings Systems 14},
The MIT Press, 2002. }
\bibitem{UCI92} {\small Murphy, P. and Aha, D., ''UCI Repository of Machine
Learning Databases [machine-readable data repository],'''' University of
California, Department of Information and Computer Science, Irvine, CA. }
\bibitem{Vapnik95} {\small Vapnik, V. N., ''\textit{The Nature of
Statistical Learning Theory,}'''' Springer, 1995. }
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊