\input zb-basic
\input zb-ioport
\iteman{io-port 01754734}
\itemau{de Campos, L.M.; G\'amez, J.A.; Larra\~naga, P.; Moral, S.; Romero, T.}
\itemti{Partial abductive inference in Bayesian networks: An empirical comparison between GAs and EDAs.}
\itemso{Larra\~naga, Pedro (ed.) et al., Estimation of distribution algorithms. A new tool for evolutionary computation. Boston: Kluwer Academic Publishers. Genet. Algorithms Evol. Comput. 2, 323-341 (2002).}
\itemab
Summary: Partial abductive inference in Bayesian networks is intended as the process of generating the $K$ most probable configurations for a distinguished subset of the network variables (explanation set), given some observations (evidence). This problem, also known as the maximum a posteriori problem, is known to be NP-hard, so exact computation is not always possible. As partial abductive inference in Bayesian networks can be viewed as a combinatorial optimization problem, genetic algorithms have been successfully applied to give an approximate algorithm for it {\it L. M. de Campos}, {\it J. A. G\'amez} and {\it S. Moral} [Pattern Recognit. Lett. 20, 1211-1217 (1999)]. In this work we approach the problem by means of estimation of distribution algorithms, and an empirical comparison between the results obtained by genetic algorithms and estimation of distribution algorithms is carried out.
\itemrv{~}
\itemcc{}
\itemut{most probable explanation; probabilistic reasoning; evolutionary computation; partial abductive inference; maximum a posteriori problem; genetic algorithms; estimation of distribution algorithms; Bayesian networks}
\itemli{}
\end