Simpson, Edwin and Roberts, Stephen J and Smith, Arfon and Lintott, Chris (2011) Bayesian Combination of Multiple, Imperfect Classifiers. In: NIPS 2011, December 2011, Spain.
![[img]](../style/images/fileicons/application_pdf.png)
|
PDF (Bayesian Combination of Multiple, Imperfect Classifiers)
Download (265Kb) | Preview |
|
|
PDF (Bayesian Combination of Multiple, Imperfect Classifiers)
Download (273Kb) | Preview |
Abstract
Classifier combination methods need to make best use of the outputs of multiple, imperfect classifiers to enable higher accuracy classifications. In many situations, such as when human decisions need to be combined, the base decisions can vary enormously in reliability. A Bayesian approach to such uncertain combination allows us to infer the differences in performance between individuals and to incorporate any available prior knowledge about their abilities when training data is sparse. In this paper we explore Bayesian classifier combination, using the computationally efficient framework of variational Bayesian inference. We apply the approach to real data from a large citizen science project, Galaxy Zoo Supernovae, and show that our method far outperforms other established approaches to imperfect decision combination. We go on to analyse the putative community structure of the decision makers, based on their inferred decision making strategies, and show that natural groupings are formed.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Topics > Machine Learning Work Areas > Applications Work Areas > Incentive Engineering |
| Divisions: | University of Oxford |
| Depositing User: | Angela Westley |
| Date Deposited: | 04 Nov 2011 10:41 |
| Last Modified: | 07 Aug 2012 12:24 |
| URI: | http://www.orchid.ac.uk/eprints/id/eprint/7 |
Actions (login required)
 |
View Item |
