Inductive Logic Programming At 30: A New Introduction

Inductive logic programming (ILP) is a form of machine learning. The goal ILP to induce hypothesis (a set logical rules) that generalises training examples. As turns 30, we provide new introduction the field. We introduce necessary notation and main learning settings; describe building blocks an system; compare several systems on dimensions; four (Aleph, TILDE, ASPAL, Metagol); highlight key application areas; and, finally, summarise current limitations directions for future research.