سال انتشار: ۱۳۹۰

محل انتشار: دومین کنفرانس ملی محاسبات نرم و فن آوری اطلاعات

تعداد صفحات: ۴

نویسنده(ها):

maryam valian – department of computer engineering zanjan
ali amiri – department of computer engineering zanjan university

چکیده:

learning bayesian networks BNs form data is a NP-hard problem. Therfore most score-based learning methods work with a heuristic search we could consider the problem of structural learning of BNs as an optimization problem and solve it by a PSO algorithm which is a nature-inspired population based stochastic search technique . this paper describes a method for finding the highest scoring structure among all possible structures of a bayesian network based on local best versionof the PSO algorithm the results of experiments show that the proposed algorithm outperforms the standard PSO algorithm in the structural learning BN problem