archives

MICCLLR: A Generalized Multiple-Instance Learning Algorithm Using Class Conditional Log Likelihood Ratio


Home 

About 

Browse 

Search 

Register 

Subscriptions 

Deposit Papers 

Help
    

El-Manzalawy, Yasser and Honavar, Vasant (2007) MICCLLR: A Generalized Multiple-Instance Learning Algorithm Using Class Conditional Log Likelihood Ratio. Technical Report 1, Computer Science, Iowa State University.

Full text available as:Adobe PDF

Abstract

We propose a new generalized multiple-instance learning (MIL) algorithm, MICCLLR (multiple-instance class conditional likelihood ratio), that converts the MI data into a single meta-instance data allowing any propositional classifier to be applied. Experimental results on a wide range of MI data sets show that MICCLLR is competitive with some of the best performing MIL algorithms reported in literature.

Keywords:multiple instance learning
Subjects:Computing Methodologies: ARTIFICIAL INTELLIGENCE: Learning (K.3.2)
ID code:00000530
Deposited by:Yasser El-Manzalawy on 05 March 2007



Contact site administrator at: ssg@cs.iastate.edu