Trick, Susanne ; Rothkopf, Constantin A. (2022)
Bayesian Classifier Fusion with an Explicit Model of Correlation.
The 25th International Conference on Artificial Intelligence. Valencia, Spain (30.03.2022-01.04.2022)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Combining the outputs of multiple classifiers or experts into a single probabilistic classification is a fundamental task in machine learning with broad applications from classifier fusion to expert opinion pooling. Here we present a hierarchical Bayesian model of probabilistic classifier fusion based on a new correlated Dirichlet distribution. This distribution explicitly models positive correlations between marginally Dirichlet-distributed random vectors thereby allowing explicit modeling of correlations between base classifiers or experts. The proposed model naturally accommodates the classic Independent Opinion Pool and other independent fusion algorithms as special cases. It is evaluated by uncertainty reduction and correctness of fusion on synthetic and real-world data sets. We show that a change in performance of the fused classifier due to uncertainty reduction can be Bayes optimal even for highly correlated base classifiers.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Trick, Susanne ; Rothkopf, Constantin A. |
| Art des Eintrags: | Bibliographie |
| Titel: | Bayesian Classifier Fusion with an Explicit Model of Correlation |
| Sprache: | Englisch |
| Publikationsjahr: | 28 September 2022 |
| Ort: | Valencia, Spain |
| Verlag: | PMLR |
| Buchtitel: | Proceedings of The 25th International Conference on Artificial Intelligence and Statistics |
| Reihe: | Proceedings of Machine Learning Research |
| Band einer Reihe: | 151 |
| Veranstaltungstitel: | The 25th International Conference on Artificial Intelligence |
| Veranstaltungsort: | Valencia, Spain |
| Veranstaltungsdatum: | 30.03.2022-01.04.2022 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Combining the outputs of multiple classifiers or experts into a single probabilistic classification is a fundamental task in machine learning with broad applications from classifier fusion to expert opinion pooling. Here we present a hierarchical Bayesian model of probabilistic classifier fusion based on a new correlated Dirichlet distribution. This distribution explicitly models positive correlations between marginally Dirichlet-distributed random vectors thereby allowing explicit modeling of correlations between base classifiers or experts. The proposed model naturally accommodates the classic Independent Opinion Pool and other independent fusion algorithms as special cases. It is evaluated by uncertainty reduction and correctness of fusion on synthetic and real-world data sets. We show that a change in performance of the fused classifier due to uncertainty reduction can be Bayes optimal even for highly correlated base classifiers. |
| Fachbereich(e)/-gebiet(e): | 03 Fachbereich Humanwissenschaften 03 Fachbereich Humanwissenschaften > Institut für Psychologie 03 Fachbereich Humanwissenschaften > Institut für Psychologie > Psychologie der Informationsverarbeitung Zentrale Einrichtungen Zentrale Einrichtungen > Centre for Cognitive Science (CCS) |
| Hinterlegungsdatum: | 28 Sep 2022 13:06 |
| Letzte Änderung: | 28 Sep 2022 13:06 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum