請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65009完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林軒田(Hsuan-Tien Lin) | |
| dc.contributor.author | Po-Lung Chen | en |
| dc.contributor.author | 陳柏龍 | zh_TW |
| dc.date.accessioned | 2021-06-16T23:14:53Z | - |
| dc.date.available | 2017-08-03 | |
| dc.date.copyright | 2012-08-03 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-08-03 | |
| dc.identifier.citation | N. Abe, B. Zadrozny, and J. Langford. An iterative method for multi-class cost-sensitive
learning. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, 2004. Brigham Anderson and Andrew Moore. Active learning for hidden markov models: objective functions and algorithms. In Proceedings of the 22nd international conference on Machine learning, 2005. L. Breiman. Random forests. Machine Learning, 2001. C. C. Chang and C. J. Lin. LIBSVM: a library for support vector machines, 2001. C. Cortes and V. Vapnik. Support-vector networks. Machine Learnning, 1995. Sanjoy Dasgupta and Daniel Hsu. Hierarchical sampling for active learning. In Proceedings of the 25th international conference on Machine learning, 2008. P. Domingos. MetaCost: A General Method for Making Classifiers Cost-Sensitive. In Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining, 1999. C. Elkan. The foundations of cost-sensitive learning. In Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2, 2001. R. E. Fan, K. W. Chang, C. J. Hsieh, X. R. Wang, and C. J. Lin. LIBLINEAR: A Library for Large Linear Classification. Journal of Machine Learning Research, 2008. M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H.Witten. The WEKA data mining software: an update. SIGKDD Explorations, 2009. S. J. Huang, R. J., and Z. H. Zhou. Active learning by querying informative and representative examples. In Advances in Neural Information Processing Systems 23, 2010. T. K. Huang, R. C. Weng, and C. J. Lin. Generalized Bradley-Terry Models and Multi- Class Probability Estimates. Journal of Machine Learning Research, 2006. P. Jain and A. Kapoor. Active learning for large multi-class problems. IEEE Conference on Computer Vision and Pattern Recognition, 2009. A. J. Joshi, F. Porikli, and N. Papanikolopoulos. Multi-class active learning for image classification. IEEE Conference on Computer Vision and Pattern Recognition, 2009. T. Luo, K. Kramer, D. B. Goldgof, L. O. Hall, S. Samson, A. Remsen, and T. Hopkins. Active Learning to Recognize Multiple Types of Plankton. Journal of Machine Learning Research, 2005. H. T. Nguyen and A. Smeulders. Active learning using pre-clustering. In Proceedings of the twenty-first international conference on Machine learning, 2004. J. C. Platt. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. In ADVANCES IN LARGE MARGIN CLASSIFIERS, 1999. B. Settles. Active Learning Literature Survey. Technical report, University ofWisconsin– Madison, 2009. Simon Tong and Daphne Koller. Support vector machine active learning with applications to text classification. Journal of Machine Learning Research, 2002. H. H. Tu and H.T. Lin. One-sided support vector regression for multiclass cost-sensitive classification. In Proceedings of the 27th International Conference on Machine Learning, 2010. A. Vlachos. A stopping criterion for active learning. Computer Speech & Language, 2008. R. Yan and A. Hauptmann. Multi-class active learning for video semantic feature extraction. In IEEE International Conference on Multimedia and Expo, 2004. R. Yan, J. Yang, and A. Hauptmann. Automatically Labeling Video Data Using Multiclass Active Learning. In Proceedings of the Ninth IEEE International Conference on Computer Vision, 2003. X. Zhu. Semi-supervised learning with graphs. PhD thesis, Carnegie Mellon University, 2005. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65009 | - |
| dc.description.abstract | 如何對成本導向(cost-sensitive)的多重分類法(multiclass classification)做主動學習(active learning)是一個相對較新的研究方向。對於這個問題，我們在這份論文中提出兩種專注於成本導向的主動學習策略：
最大預期成本(maximum expected cost)以及最小成本差距(cost-weighted minimum margin)。這兩種策略皆可以被視為是現存非成本導向(costinsensitive)策略的延伸。實驗結果顯示，在成本導向的環境下成本導 向的策略表現相當理想， 性能明顯超越非成本導向的策略。實驗結果中也反映出學習資料的難易度會若干影響成本導向主動學習演算法的表現。因此在實際的主動學習的應用中，根據分析資料特性來選擇主動學習的策略是較理想的做法。 | zh_TW |
| dc.description.abstract | Multiclass cost-sensitive active learning is a relatively new problem. In this thesis, we derive the maximum expected cost and cost-weighted minimum margin strategy for multiclass cost-sensitive active learning. These two strategies can be seem as the extended version of classical cost-insensitive active learning strategies. The experimental results demonstrate that the derived strategies are promising for cost-sensitive active learning. In particular, the cost-sensitive strategies outperform cost-insensitive ones on many benchmark data sets. The results also reveal how the hardness of data affects the performance of active learning strategies. Thus, in practical active learning applications, data analysis before strategy selection can be important. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T23:14:53Z (GMT). No. of bitstreams: 1 ntu-101-R99922038-1.pdf: 1911477 bytes, checksum: b0918b658da71e5e8c9122378ac6bbc7 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | 致謝i
中文摘要iii Abstract v 1 Introduction 1 2 Problem setup 5 2.1 Multiclass active learning . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 Pool-based setup . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Cost-sensitive active learning . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2.1 Multiclass cost-sensitive classifier . . . . . . . . . . . . . . . . . 7 3 Existing active learning strategies 9 3.1 Binary active learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.2 Multiclass active learning . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.2.1 Minimum confidence . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.2 Minimum margin . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2.3 Maximum entropy . . . . . . . . . . . . . . . . . . . . . . . . . 13 4 Strategies for cost-sensitive active learning 15 4.1 Strategy: maximum expected cost . . . . . . . . . . . . . . . . . . . . . 15 4.1.1 Basic idea . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.1.2 Maximum expected cost reduction . . . . . . . . . . . . . . . . . 16 4.1.3 Approximation . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.4 Relationship between minimum confidence and maximum expected cost . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.2 Strategy: cost-weighted minimum margin . . . . . . . . . . . . . . . . . 18 5 Experiments 19 5.1 Experiment settings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5.2 Comparison of strategies . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5.3 Comparison of strategies on artificial datasets . . . . . . . . . . . . . . . 25 5.4 The effects from data characteristics . . . . . . . . . . . . . . . . . . . . 27 6 Conclusion 31 Bibliography 33 A Extended cost-sensitive strategies related to maximum entropy 37 | |
| dc.language.iso | en | |
| dc.subject | 電腦科學 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 多重分類 | zh_TW |
| dc.subject | 成本導向 | zh_TW |
| dc.subject | 主動學習演算法 | zh_TW |
| dc.subject | Cost-sensitive | en |
| dc.subject | Machine Learning | en |
| dc.subject | Computer Science | en |
| dc.subject | Multi-class Classification | en |
| dc.subject | Active Learning | en |
| dc.title | 使用機率模型實行成本導向多重分類的主動學習演算法 | zh_TW |
| dc.title | Active Learning for Multiclass Cost-sensitive Classification Using Probabilistic Models | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林守德(Shou-De Lin),李育杰(Yuh-Jye Lee) | |
| dc.subject.keyword | 電腦科學,機器學習,多重分類,成本導向,主動學習演算法, | zh_TW |
| dc.subject.keyword | Computer Science,Machine Learning,Multi-class Classification,Cost-sensitive,Active Learning, | en |
| dc.relation.page | 38 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2012-08-03 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-101-1.pdf 未授權公開取用 | 1.87 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。