.png){kind=icon}
Return
A maximum-margin multisphere approach for binary Multiple Instance Learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ejor.2021.11.022.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a heuristic approach for solving binary Multiple Instance Learning (MIL) problems, whose objective is to categorize bags of instances. Considering the case with two classes of instances, on the basis of the standard MIL assumption, a bag is classified positive if it contains at least a positive in-stance and negative if all its instances are negative. Inspired by a well-established MIL Support Vector Machine type approach, our technique is based on iteratively separating the bags by means of successive maximum-margin spheres. Such spheres, whose number is automatically determined, are generated by computing, for each of them, the optimal radius in correspondence to a prefixed center. Numerical results are presented on a set of benchmark test problems, showing the effectiveness of our approach. (c) 2021 Elsevier B.V. All rights reserved.
Keywords:
Machine learning
Multiple Instance Learning
Spherical separation
Fixed-center margin maximization
Journal
IF:
6
Papers:
2.2W
Citations:
6.4W
Organization
Cited Papers
Water Use Patterns of Sympatric Przewalski’s Horse and Khulan: Interspecific Comparison Reveals Niche Differences.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveClassification in the multiple instance learning framework via spherical separationSOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more