A genetic algorithm-based ILP incremental system

Inductive learning has been employed successfully in various domains, however the inductive logic programming (ILP) systems focused on non-incremental learning tasks where independent sets of data are provided incoherently. In this paper, we propose a new genetic algorithm-based ILP system, called GAILP, for incremental learning. GAILP is a covering algorithm which extracts hypotheses/rules from a collection of examples in a reliable way. It employs a genetic algorithm technique to discover various aspects of the potential combinations. GAILP induces every possible rule for the given combination and selects the most generic ones among them. It also eliminates rules which might become obsolete by the existence of more generic rules. Unlike other ILP systems, GAILP batches all given examples and background knowledge, then it groups the examples and prioritizes the induction process. This prioritization needs to be done to preserve dependency and to revise theory. The paper introduces GAILP's fundamentals mechanisms and demonstrates its algorithms with a running example.