Bowes, J., Neufeld, E., Greer, J. E. and Cooke, J., A Comparison of Association Rule Discovery and Bayesian Network Causal Inference Algorithms to Discover Relationships in Discrete Data, Proceedings of the Thirteenth Canadian Artificial Intelligence Conference (AI'  Home/Search   Document Details and Download   Summary   Related Articles

....if we observe that (x = 5) is always true when (y = 2) then we could predict the value of y as 2 when we see that x is 5. Alternatively, we could assume that we have the rule: if (x = 5) then (y = 2) and use it to set the value of y to 2 by setting the value of x to 5. Some researchers [1, 10] have tried to find the stronger notion of causality among the observed variables. In the previous example, they may call x a cause of y. In this paper we consider two approaches to the problem of finding relations among variables. TETRAD [9] is a well known causality miner that uses Bayesian ....

....we consider two approaches to the problem of finding relations among variables. TETRAD [9] is a well known causality miner that uses Bayesian networks [3] to find causal relations. One example of the type of rules discovered by TETRAD is x y, which means that x causes y. From the examples in [1, 10], it appears that Bayesian networks discover more causal relations than actually exist in the domain. Bayesian networks find causality even in domains where the existence of causal relations itself is a matter a debate. For words in political texts, Bayesian networks find rules such as Minister ....

[Article contains additional citation context not shown here]

Bowes, J., Neufeld, E., Greer, J. E. and Cooke, J., A Comparison of Association Rule Discovery and Bayesian Network Causal Inference Algorithms to Discover Relationships in Discrete Data, Proceedings of the Thirteenth Canadian Artificial Intelligence Conference (AI'

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