dc.contributor.advisor |
Lowd, Daniel |
|
dc.contributor.author |
Kelly, Austen |
|
dc.date.accessioned |
2020-02-27T22:39:55Z |
|
dc.date.available |
2020-02-27T22:39:55Z |
|
dc.date.issued |
2020-02-27 |
|
dc.identifier.uri |
https://scholarsbank.uoregon.edu/xmlui/handle/1794/25295 |
|
dc.description.abstract |
Machine learning methods often face a tradeoff between the accuracy of discriminative models and the lower sample complexity of their generative counterparts. This inspires a need for hybrid methods. In this paper we present the graphical ensemble classifier (GEC), a novel combination of logistic regression and naive Bayes. By partitioning the feature space based on known independence structure, GEC is able to handle datasets with a diverse set of features and achieve higher accuracy than a purely discriminative model from less training data. In addition to describing the theoretical basis of our model, we show the practical effectiveness on artificial data, along with the 20-newsgroups, MNIST, and MediFor datasets. |
en_US |
dc.language.iso |
en_US |
|
dc.publisher |
University of Oregon |
|
dc.rights |
All Rights Reserved. |
|
dc.subject |
machine learning |
en_US |
dc.subject |
probabilistic graphical models |
en_US |
dc.title |
Exploiting Domain Structure with Hybrid Generative-Discriminative Models |
|
dc.type |
Electronic Thesis or Dissertation |
|
thesis.degree.name |
M.S. |
|
thesis.degree.level |
masters |
|
thesis.degree.discipline |
Department of Computer and Information Science |
|
thesis.degree.grantor |
University of Oregon |
|