Learning relational dependency networks in hybrid domains (Q747248)

Statistical relational learning (SRL) aims at learning from data relational structures. This paper is about learning structures of a hybrid SRL model. The authors propose hybrid relational dependency networks (HRDNs), an extension to relational dependency networks that are able to model continuous variables. They propose an algorithm for learning both the structure and parameters of an HRDN. Then the authors provide an empirical evaluation that demonstrates the advantages of modeling continuous variables for SRL.