The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Supervised Learning in Absence of Accurate Class Labels: A Multi-Instance Learning Approach
|
|
Author(s): Ramasubramanian Sundararajan (GE Global Research, India), Hima Patel (GE Global Research, India)and Manisha Srivastava (GE Global Research, India)
Copyright: 2017
Pages: 14
Source title:
Handbook of Research on Applied Cybernetics and Systems Science
Source Author(s)/Editor(s): Snehanshu Saha (PESIT South Campus, India), Abhyuday Mandal (University of Georgia, USA), Anand Narasimhamurthy (BITS Hyderabad, India), Sarasvathi V (PESIT- Bangalore South Campus, India)and Shivappa Sangam (UGC, India)
DOI: 10.4018/978-1-5225-2498-4.ch010
Purchase
|
Abstract
Traditionally supervised learning algorithms are built using labeled training data. Accurate labels are essential to guide the classifier towards an optimal separation between the classes. However, there are several real world scenarios where the class labels at an instance level may be unavailable or imprecise or difficult to obtain, or in situations where the problem is naturally posed as one of classifying instance groups. To tackle these challenges, we draw your attention towards Multi Instance Learning (MIL) algorithms where labels are available at a bag level rather than at an instance level. In this chapter, we motivate the need for MIL algorithms and describe an ensemble based method, wherein the members of the ensemble are lazy learning classifiers using the Citation Nearest Neighbour method. Diversity among the ensemble methods is achieved by optimizing their parameters using a multi-objective optimization method, with the objective being to maximize positive class accuracy and minimize false positive rate. We demonstrate results of the methodology on the standard Musk 1 dataset.
Related Content
|
Man Tianxing, Vasiliy Yurievich Osipov, Ildar Raisovich Baimuratov, Natalia Alexandrovna Zhukova, Alexander Ivanovich Vodyaho, Sergey Vyacheslavovich Lebedev.
© 2020.
27 pages.
|
|
Alexey Kashevnik, Nikolay Teslya.
© 2020.
23 pages.
|
|
Sergey Vyacheslavovich Lebedev, Michail Panteleyev.
© 2020.
26 pages.
|
|
Valentin Olenev, Yuriy Sheynin, Irina Lavrovskaya, Ilya Korobkov, Lev Kurbanov, Nadezhda Chumakova, Nikolay Sinyov.
© 2020.
42 pages.
|
|
Konstantin Nedovodeev, Yuriy Sheynin, Alexey Syschikov, Boris Sedov, Vera Ivanova, Sergey Pakharev.
© 2020.
34 pages.
|
|
Andrey Kuzmin, Maxim Safronov, Oleg Bodin, Victor Baranov.
© 2020.
23 pages.
|
|
Alexander Yu. Meigal, Dmitry G. Korzun, Alex P. Moschevikin, Sergey Reginya, Liudmila I. Gerasimova-Meigal.
© 2020.
26 pages.
|
|
|