构建新包空间的多示例学习方法

温超; 耿国华; 李展

您当前的位置：

首页 >

文章列表页 >

构建新包空间的多示例学习方法

更新时间：2025-07-09

- 构建新包空间的多示例学习方法
- Multiple Instance Learning Method Based on Building New Bag Space
- 西安交通大学学报 2011年45卷第8期页码：62-66+117
- 作者机构：
  
  西北大学信息科学与技术学院,西安,710069
- 作者简介：
- 基金信息：
  
  : 2011-03-03. 作者简介: 温超(1978-),男,博士生;耿国华(联系人),女,教授,博士生导师. 基金项目: 国家自然科学基金资助项目(60873094);高等学校博士学科点专项科研基金资助项目(200806970014)
- DOI：
  中图分类号： TP18
- 网络首发：2011-08-10，
  
  纸质出版：2011
- 稿件说明：
移动端阅览
温超, 耿国华, 李展. 构建新包空间的多示例学习方法[J]. 西安交通大学学报, 2011,45(8):62-66+117.

Multiple Instance Learning Method Based on Building New Bag Space[J]. 2011, 45(8): 62-66+117.
温超, 耿国华, 李展. 构建新包空间的多示例学习方法[J]. 西安交通大学学报, 2011,45(8):62-66+117. DOI：

Multiple Instance Learning Method Based on Building New Bag Space[J]. 2011, 45(8): 62-66+117. DOI：

摘要

针对已有神经网络方法采用示例决定标记从而导致多示例学习(MIL)中包结构信息丢失的问题

提出了一种新的RK_BP多示例学习方法.在示例空间

首先采用粗糙集对其进行属性约简; 然后进行K均值聚类

利用聚类点构造新包空间; 在新空间中

利用误差反向传播神经网络算法进行分类.在多个测试数据集上对算法进行测试

结果表明该算法可有效解决已有神经网络方法包结构信息丢失问题

明显提高分类性能.

Abstract

Aiming at bag structure information loss problem caused by single instance deciding bag label in multiple instance learning(MIL)

a new MIL algorithm named RK_BP is proposed. Firstly

rough set method is adopted to reduce the redundant information in the instance feature space

then K means algorithm is applied to cluster and build a new bag space

and finally back propagation algorithm is used to classify bags in the new space. Experiments on data sets show that this algorithm deals well with the multiple instance problems and provides better classification results.

关键词

Keywords

references

DIETTERICH T G, LATHROP R H, LOZANO-PÉREZ T. Solving the multiple instance problem withaxis-parallel rectangles [J]. Artificial Intelligence, 1997, 89(1/2): 31-71.

MARON O, LOZANO-PÉREZ T. Advances in neural information processing systems 10: a framework for multiple-instance learning [M]. Cambridge, MA,USA: MIT Press, 1998:570-576.

ZHANG Qi, GOLDMAN S A. Advances in neural Information processing systems 14: EM-DD: an improved multiple-instance learning technique [M]. Cambridge, MA,USA: MIT Press, 2002: 1073-1080.

ANDREWS S, HOFMANN T, TSOCHANTARIDIS I. Multiple instance learning with generalized support vector machines [C]∥Proceedings of the 18th National Conference on Artificial Intelligence. Edmonton, Canada: AAAI Press, 2002: 943-944.

GARTNER T, FLACH P A, KOWALCZYK A, et al. Multi-instance kernels [C]∥Proceedings of the 19th International Conference on Machine Learning. San Francisco, CA, USA: Morgan Kaufmam Publishers Inc, 2002:179-186.

WANG Huayan, YANG Qiang, ZHA Hongbin. Adaptive p-posterior mixture-model kernels for multiple instance learning [C]∥Proceedings of the 25th International Conference on Machine Learning. Helsinki, Finland: ACM Press, 2008: 1136-1143.

ZHOU Zhihua, SUN Yuyin, LI Yufeng. Multi-instance learning by treating instances as non-I.I.D. samples [C]∥Proceedings of the 26th International Conference on Machine Learning. Quebec, Canada:[n.s.], 2009:1249-1256.

詹德川, 周志华. 基于流形学习的多示例回归算法 [J].计算机学报, 2006,29(11):1948-1955.

ZHAN Dechuan. ZHOU Zhihua. A manifold learning-based multi-instance regression algorithm [J].Chinese Journal of Computers, 2006,29(11):1948-1955.

ZHOU Zhihua, ZHANG Minling. Neural networks for multi-instance learning[C]∥Proceedings of the International Conference on Intelligent Information Technology. Beijing, China: People's Post and Telecommunications Publishing House, 2002: 455-459.

ZHANG Minling, ZHOU Zhihua. Adapting RBF neural networks to multi-instance learning[J]. Neural Processing Letters, 2006, 23(1): 1-26.

ZHANG Minling, ZHOU Zhihua. Improve multi-instance neural networks through feature selection [J]. Neural Processing Letters, 2004, 19(1): 1-10.

HU Qinhua, YU Daren, XIE Zongxia. Numerical attribute reduction based on neighborhood granulation and rough approximation [J]. Journal of Software, 2008,19(3): 640-649.

RUMELHART D E, HINTON G E, WILLIAMS R J. Learning internal representations by error propagation [C]∥Parallel Distributed Processing: Explorations in the Microstructure of Cognition:Vol 1 Foundations. Cambridge, MA, USA: MIT Press, 1986: 318-362.

PAWLAK Z. Rough set [J].International Journal of Computer and Information Sciences,1982,11:341-356.

CHEN Yixin, WANG J Z. Image categorization by learning and reasoning with regions [J]. Journal of Machine Learning Research, 2004, 5(8):913-939.

KWOK J T, CHEUNG P M. Marginalized multi-instance kernels [C]∥Proceedings of the 20th International Joint Conference on Artificial Intelligence. Hydrabad, India: AAAI Press, 2007: 901-906.

MACQUEEN J. Some methods for classification and analysis of multivariate observations [C]∥Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Berkeley,CA, USA:University of California Press, 1967: 281-297.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

粒度计算中混合属性约简的权重模糊粗糙集模型

粗糙集高效遗传约简算法

面向元信息分类的支持向量机改进技术

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究

离子液体改性燃料的电流体动力学效应研究