Slęzak D., Wróblewski J., 2002. Order-based genetic algorithms for extraction of approximate bayesian networks from data. In: Proc. of 9th International Conference on Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU 2002), Annecy, France. ESIA - Universite de Savoie, France 2002, vol. 3, 1645 - 1651.
ABSTRACT
Approximate bayesian nets (a-BN's) almost keep the information entropy of data tables and encode knowledge about approximate dependencies between features. Advantages of applying a-BN's to real-life data analysis are discussed. Genetic-based algorithmic framework for extracting a-BN's from data is proposed.