Background Knowledge in the Tertius First Order Knowledge Discovery Tool

This paper describes the three formalism available for specifying background knowledge in the Tertius first order logic discovery tool. It also describes the way background knowledge effects the results of Tertius. The way Tertius handles integrity constraints is compared to an approach suggested in work done on the CLAUDIEN [1] learning system. Finally a number of examples of use of Tertius for analysing the ’audiology’ dataset 1 are also provided. 1The ’audiology’ data-set is taken from the University of California at Irvine’s Machine Learning Repository; http://www.ics.uci.edu/AI/ML/MLDBRepository.html