Learning Relations: Basing Top-Down Methods on Inverse Resolution

Top-down algorithms for relational learning specialize general rules un- til they are consistent , and are guided by heuristics of different kinds.In general, a correct solutiion is not guaranteed. By contrast, bottom-up methods are well formalized, usually within the framework of inverse reso- lution.Inverse resolution has also been used as an efficient tool for deduc- tive reasoning, and here we prove tha input refutations can be translated into inverse unit refutations.This result allows us to show that top-down learning methods can be also described by means of inverse resolution, yielding a unified theory of relational learning.