Birgit Tausend

Learn More
Interest in Declarative bias in Machine Learning is growing with the expressivity of the concept description language of ML systems. Inductive Logic Programming more than any other ML eld is thus concerned with explicitely biasing learning. The main issues already identiied in declarative bias RG90] have been studied within the ILP project, i.e. the(More)
Restrictions on the number and depth of existential variables as deened in the language series of Clint Rae92] are widely used in ILP and expected to produce a considerable reduction in the size of the hypothesis space. In this paper we show that this is generally not the case. The lower bounds we present lead to intractable hypothesis spaces except for toy(More)