|
KU ScholarWorks >
School of Business >
School of Business Articles >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1808/520
|
|
View usage statistics
|
| Title: | Hybrid Bayesian Networks with Linear Deterministic Variables |
| Authors: | Cobb, Barry R.
Shenoy, Prakash P. |
| Keywords: | Hybrid Bayesian networks
Conditionally deterministic variables
Linear Deterministic Functions
Shenoy-Shafer Architecture |
| Issue Date: | Jul-2005 |
| Publisher: | Association for Uncertainty in Artificial Intelligence |
| Extent: | 504200 bytes |
| Type: | Book chapter |
| Citation: | Cobb, B. R. and P. P. Shenoy (2005), "Hybrid Bayesian networks with linear deterministic variables," in F. Bacchus and T. Jaakkola (eds.), Uncertainty in Artificial Intelligence: Proceedings of the Twenty-First Conference (UAI-05), pp. 136--144, AUAI Press, Corvallis, OR. |
| Abstract: | When a hybrid Bayesian network has conditionally
deterministic variables with continuous parents, the joint density function for the continuous variables does not exist. Conditional linear Gaussian distributions can handle such cases when the continuous variables have a multi-variate normal distribution and the discrete variables do not have continuous parents. In this paper, operations required for performing inference with
conditionally deterministic variables in hybrid Bayesian networks are developed. These methods allow inference in networks with deterministic
variables where continuous variables may be non-Gaussian, and their density functions can be approximated by mixtures of truncated exponentials. There are no constraints on the placement of continuous and discrete nodes in the network. |
| URI: | http://hdl.handle.net/1808/520 |
| ISBN: | 0-9749039-1-4 |
| Appears in Collections: | School of Business Articles
|
Items in KU ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
|
top