Cheng, J., Bell, D.A. and Liu, W. (1997). An Algorithm for Bayesian Belief Network Construction from Data. Proc, 6th International Workshop on Artificial Intelligence and Statistics. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Bayesian Belief Networks for Data Mining - Steck, Tresp (1996) (1 citation) (Correct)
....search for the best structure and is therefore computationally very expensive and not directly applicable to data mining applications. In this paper we pursue a constraint based approach similar to the ones in [Wermuth and Lauritzen 1983, Fung and Crawford 1990, Spirtes et al. 1993, Suzuki 1996, Cheng et al. 1997] The basic idea of those algorithms is to derive a set of CIDSs from the data without taking into account the Bayesian network structure. The Bayesian network is then constructed from the CIDSs in a later step. This is done in standard algorithms by removing an edge in the Bayesian network ....
....and the same statements apply as for the SGS algorithm. 3 26 18 25 17 6 10 21 11 27 34 15 22 23 13 16 37 36 24 35 1 2 32 31 20 19 4 5 29 28 7 8 9 30 14 33 12 Figure 2: The alarm network contains 37 variables and 46 edges. The numbering of the variables is chosen as in [Cheng et al. 1997]. in [Spirtes et al. 1993] it is understood that this implies a (conditional) dependence. 4.2 RULES For each given CIS of the form I(a; bjS) with D(a; bjS 0 ) 8S 0 ae S the proposed Necessary Path Condition requires the absence of the edge [a; b] and the presence of the paths between a ....
[Article contains additional citation context not shown here]
J. Cheng, D. A. Bell, W. Liu. An Algorithm for Bayesian Belief Network Construction from Data, AI & STAT, 1997; Learning Belief Networks from Data: An Information Theory Based Approach, CIKM, 1997.
Learning Bayesian Networks from Data: - An Information-Theory Based Self-citation (Cheng Bell Liu) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W., An algorithm for Bayesian belief network construction from data, Proceedings of AI & STAT'97 (pp.83-90), Ft. Lauderdale, Florida, 1997.
Learning Bayesian Belief Network Classifiers: Algorithms and.. - Cheng, Greiner (2001) (8 citations) Self-citation (Cheng) (Correct)
....independence relationships among the nodes, according to the concept of d separation ( 22] This sug gests learning the BN structure by identifying the conditional independence relationships among the nodes. These algorithms are referred as CI based algorithms or constraint based algorithms ( 23][1]) Friedman et al. 1997) show theoretically that the general scoring based methods may result in poor classifiers since a good classifier maximizes a different function viz. classification accuracy. Greiner et al. 1997) reach the same conclusion, albeit via a different analysis. Moreover, ....
....subsets. 3.1 . The Learning Algorithms for Multi nets and GBNs Fig. 3 and Fig. 4 sketches the algorithms for learning multi nets and GBNs. They each use the CBL algorithms, which are general purpose BN learning algorithms: one for the case when node ordering is given (the CBL 1 algorithm [1]) the other for the case when node ordering is not given (the CBL 2 algorithm [2] Both CBL 1 and CBL 2 are CI based algorithms that use information theory for dependency analysis. CBL 1 requires ) 2 N O mutual information tests to learn a general BN over N attributes, and CBL 2 requires ) ....
[Article contains additional citation context not shown here]
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Learning Bayesian Belief Network Classifiers: Algorithms and.. - Cheng, Greiner (2001) (8 citations) Self-citation (Cheng) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Learning Bayesian Belief Network Classifiers: Algorithms and.. - Cheng, Greiner (2001) (8 citations) Self-citation (Cheng) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Comparing Bayesian Network Classifiers - Cheng, Greiner (1999) (17 citations) Self-citation (Cheng) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Learning Bayesian Networks from Data: An Efficient Approach.. - Cheng, Bell, Liu (1997) (4 citations) Self-citation (Cheng Bell Liu) (Correct)
....95, Windows 98 and Windows NT) on PCs. The system takes as input a database table and constructs a Bayesian network (both structure parameters) as output. It also supports domain knowledge as additional input. Our system is available for download from our web site (http: www.cs. ualberta.ca jcheng bnpc.htm) Since October 1997, over 2,000 people have visited Tuberculosis XRay Result Tuberculosis or Cancer Lung Cancer Dyspnea Bronchitis Visit To Asia Smoking 31 our web sites and over 1000 people have downloaded our system. We are also very glad to know that some users have used it on real world problems. Next, we ....
Cheng, J., Bell, D.A. and Liu, W., An algorithm for Bayesian belief network construction from data, Proceedings of AI & STAT'97 (pp.83-90), Ft. Lauderdale, Florida, 1997.
Comparing Bayesian Network Classifiers - Cheng, Greiner (1999) (17 citations) Self-citation (Cheng) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Comparing Bayesian Network Classifiers - Cheng, Greiner (1999) (17 citations) Self-citation (Cheng) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997a). An algorithm for Bayesian belief network construction from data. In Proceedings of AI & STAT'97 (pp.83-90), Florida.
Learning Belief Networks from Data: An Information Theory.. - Cheng, Bell, Liu (229 citations) Self-citation (Cheng Bell Liu) (Correct)
....node 32 or 34 is instantiated. It may suggest that the relationship between this pair of nodes can be expressed through other dependency relationships. The result on dataset3 also missed two other edges; however, this is due to the fact that 12 32 and 21 31 are actually independent in dataset3 [Cheng et al. 1997]. The independence between 21 and 31 also causes an extra un oriented edge 22 31. From these tables, we can see that our results are very encouraging. The algorithm has also been successfully implemented in several real world applications. One of them is a telecommunication fault diagnosis system ....
....[Singh and Valtorta, 1995] do not require node ordering. Other algorithms [Cooper and Herskovits, 1992; Herskovits, 1991; Suzuki, 1996; Wermuth and Lauritzen, 1983; Srinivas et al. 1990] deal with a rather special case where node ordering is known. In this special case, our simplified algorithm [Cheng et al. 1997] require O N ( 2 times of CI tests and is correct when the underlying model is DAG faithful. On the three data sets of ALARM network used in this paper, the simplified algorithm in this special case runs 25 faster and constructs the network with fewer errors than that in the general ....
Cheng, J., Bell, D.A. and Liu, W., An algorithm for Bayesian belief network construction from data, Proceedings of AI & STAT'97 (pp.83-90), Ft. Lauderdale, Florida, 1997.
The Performance of Bayesian Network Classifiers Constructed Using .. - Madden (2003) (Correct)
No context found.
Cheng, J., Bell, D.A. and Liu, W. (1997). An Algorithm for Bayesian Belief Network Construction from Data. Proc, 6th International Workshop on Artificial Intelligence and Statistics.
On a Non-Local Search Strategy for Learning in Bayesian Networks - Steck (Correct)
No context found.
J. Cheng, D. A. Bell, and W. Liu, `An Algorithm for Bayesian Belief Network Construction from Data', AI & STAT, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC