DMCA
The Representational Power of Discrete Bayesian Networks (2002)
Cached
Download Links
| Venue: | JOURNAL OF MACHINE LEARNING RESEARCH |
| Citations: | 6 - 0 self |
BibTeX
@MISC{Ling02therepresentational,
author = {Charles X. Ling and Huajie Zhang},
title = {The Representational Power of Discrete Bayesian Networks},
year = {2002}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
One of the most important fundamental properties of Bayesian networks is the representational power, re ecting what kind of functions they can or cannot represent. In this paper, we establish an association between the structural complexityofBayesian networks and their representational power. We use the maximum number of nodes' parents as the measure for the Bayesian network structural complexity, and the maximum XOR contained in a target function as the measure for the function complexity. A representational upper bound is established and proved. Roughly speaking, discrete Bayesian networks with each node having at most k parents cannot represent any function containing (k+1)-XORs. Our theoretical results help us to gain a deeper understanding on the capacities and limitations of Bayesian networks.
Keyphrases
representational power discrete bayesian network bayesian network important fundamental property representational upper bound maximum xor function complexity maximum number bayesian network structural complexity roughly speaking structural complexityofbayesian network function containing target function theoretical result
