- 期刊
Multiple Instance Learning with Correlated Features
並列摘要
Multiple-instance learning (MIL) has received increasing amount of research interest in machine learning recent years for its wide applications in image classification, text categorization, computer security, etc. Unlike supervised learning, in MIL, only the labels of bags are known, the instance labels in positive bags are not available. Many algorithms make the assumption that the instances in the bags are i.i.d samples, but this may not true in practical applications. In this paper, we treat the negative instances in the positive bag as pairwise partners of the positive instances, by using this correlation information, efficient feature is built to describe the bag. Experiment results show that this description is efficient in real world applications.
延伸閱讀
- Li, W. R. (2013). Fast Sparse Coding for Unsupervised Feature Learning [master's thesis, National Tsing Hua University]. Airiti Library. https://doi.org/10.6843/NTHU.2013.00795
- 林義朝（2004）。Learning Profile Mining Using Structuralized Learning Feature〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu200400211
- Chow, K. P. (2000). Load-balancing in distributed multi-agent computing [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200006011
- Hsu, H. N. (2022). Modeling Feature Combination for User Preference Learning [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU202203871
- 張家瑋（2011）。An Intelligent Inference Platform with Intent Detection〔碩士論文，大同大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0081-3001201315111969