Sciweavers

Share
ICMLA
2009

Learning Parameters for Relational Probabilistic Models with Noisy-Or Combining Rule

8 years 3 months ago
Learning Parameters for Relational Probabilistic Models with Noisy-Or Combining Rule
Languages that combine predicate logic with probabilities are needed to succinctly represent knowledge in many real-world domains. We consider a formalism based on universally quantified conditional influence statements that capture local interactions between object attributes. The effects of different conditional influence statements can be combined using rules such as Noisy-OR. To combine multiple instantiations of the same rule we need other combining rules at a lower level. In this paper we derive and implement algorithms based on gradient-descent and EM for learning the parameters of these multi-level combining rules. We compare our approaches to learning in Markov Logic Networks and show superior performance in multiple domains. Keywords-Relational Learning;
Sriraam Natarajan, Prasad Tadepalli, Gautam Kunapu
Added 19 Feb 2011
Updated 19 Feb 2011
Type Journal
Year 2009
Where ICMLA
Authors Sriraam Natarajan, Prasad Tadepalli, Gautam Kunapuli, Jude W. Shavlik
Comments (0)
books