MULTIVARIATE BELIEF FUNCTIONS AND GRAPHICAL MODELS
In this thesis we address computational aspects of combining belief functions over a product space. We start by reviewing the elements of the theory of belief functions which provides a generalization of traditional Bayesian inference. Multivariate belief functions and graphical models are then intr...
Saved in:
| Main Author: | |
|---|---|
| Format: | Dissertation |
| Language: | English |
| Published: |
ProQuest Dissertations & Theses
01-01-1986
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this thesis we address computational aspects of combining belief functions over a product space. We start by reviewing the elements of the theory of belief functions which provides a generalization of traditional Bayesian inference. Multivariate belief functions and graphical models are then introduced. The graphs we associate with a belief function reflect Markov-like relations between variables. Efficient algorithms for computing marginal belief functions can be developed using the graphs. We apply these algorithms to a medical diagnostic model. Other applications are also suggested. |
|---|---|
| ISBN: | 9798643136941 |