An approach to learning Bayesian networks from small data set

Bayesian networks are graphical representations of dependency relationships between random variables.The current research focus on learning from the complete data set and the incomplete data set,requiring large data set.But sometimes only small data set can be got in the real-world situation.A new method of learing Bayesian networks from small data set is presented genetic algorithm based on Bootstrap sampling.Experimental results show that the method is an efficient way to learn Bayesian networks from small data set.