Knowledge Engineering for Large Belief Networks

Pradhan, Malcolm; Provan, Gregory; Middleton, Blackford; Henrion, Max

doi:10.1016/b978-1-55860-332-5.50066-3

Cited by 86 publications

(57 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pradhan et al [6] proposed an algorithm exploiting cumulative probability distributions for efficient calculation of the MAX-based CPT that computes parameters of the MAX-based CPT as follows:…”

Section: Definition 3 (Max-based Cpt) a Max-based Cpt Prq(y |P) Is A mentioning

confidence: 99%

See 1 more Smart Citation

Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice?

Zagorecki

Drużdżel

2013

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Abstract.One problem faced in knowledge engineering for Bayesian networks is the exponential growth of the number of parameters in their conditional probability tables (CPTs). The most common practical solution is application of the noisy-OR (or their generalization, the noisy-MAX) gates, which take advantage of independence of causal interactions and provide a logarithmic reduction of the number of parameters required to specify a CPT. In this paper, we propose an algorithm that fits a noisy-MAX distribution to an existing CPT and we apply it to search for noisy-MAX gates in three existing practical Bayesian networks. We show that noisy-MAX gate provides a surprisingly good fit for as many as 50% of CPTs in these networks. The importance of this finding is that it provides an empirical justification for the use of the noisy-MAX gate as a powerful knowledge engineering tool.

show abstract

Section: Definition 3 (Max-based Cpt) a Max-based Cpt Prq(y |P) Is A mentioning

confidence: 99%

“…Noisy-OR and noisy-MAX gates have proven their worth in many real-life applications (e.g., [5,6,7]). Their foremost advantage is a small number of parameters that are sufficient to specify the entire CPT.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice?

Zagorecki

Drużdżel

2013

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

show abstract

“…The first condition is justified by the following observation. Reinforcement and undermining capture intuitive patterns of causal interactions, and reinforcement-based causal models, such as the noisy-OR, have been widely applied, e.g., [PPMH94]. The second condition is justified by the knowledge engineering practice in building BNs, where numerical probabilities have been either elicited from experts or learned from available data.…”

Section: Approach and Assumptionmentioning

confidence: 99%

Acquisition of Causal Models for Local Distributions in Bayesian Networks

Xiang

Truong

2014

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-To specify a Bayesian network, a local distribution in the form of a conditional probability table, often of an effect conditioned on its n causes, needs to be acquired, one for each non-root node. Since the number of parameters to be assessed is generally exponential in n, improving the efficiency is an important concern in knowledge engineering. Non-impeding noisy-AND (NIN-AND) tree causal models reduce the number of parameters to being linear in n, while explicitly expressing both reinforcing and undermining interactions among causes. The key challenge in NIN-AND tree modeling is the acquisition of the NIN-AND tree structure. In this work, we formulate a concise structure representation and an expressive causal interaction function of NIN-AND trees. Building on these representations, we propose two structural acquisition methods, which are applicable to both elicitation-based and machine learning-based acquisitions. Their accuracy is demonstrated through experimental evaluations.

show abstract

“…When a BBN model is used as a probabilistic reasoning engine, the validation requires a complex and challenging approach, wherein a multitude of validation-related activities must be performed [2][3][4][5] and as part of one such activity, queries must be formed and posed to the network. Any subset of variables might be considered as evidence in such a query, which leads to the need to formulate an inordinate number of queries based on various subsets of variables.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Discovery for Query Formulation for Validation of a Bayesian Belief Network

Serpen

Riesen²

2010

JILSA

View full text Add to dashboard Cite

This paper proposes machine learning techniques to discover knowledge in a dataset in the form of if-then rules for the purpose of formulating queries for validation of a Bayesian belief network model of the same data. Although domain expertise is often available, the query formulation task is tedious and laborious, and hence automation of query formulation is desirable. In an effort to automate the query formulation process, a machine learning algorithm is leveraged to discover knowledge in the form of if-then rules in the data from which the Bayesian belief network model under validation was also induced. The set of if-then rules are processed and filtered through domain expertise to identify a subset that consists of "interesting" and "significant" rules. The subset of interesting and significant rules is formulated into corresponding queries to be posed, for validation purposes, to the Bayesian belief network induced from the same dataset. The promise of the proposed methodology was assessed through an empirical study performed on a real-life dataset, the National Crime Victimization

show abstract

Knowledge Engineering for Large Belief Networks

Cited by 86 publications

References 11 publications

Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice?

Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice?

Acquisition of Causal Models for Local Distributions in Bayesian Networks

Knowledge Discovery for Query Formulation for Validation of a Bayesian Belief Network

Contact Info

Product

Resources

About