ILP for Bootstrapped Learning: A Layered Approach to Automating the ILP Setup Problem
Sriraam Natarajan, Gautam Kunapuli, Richard Maclin, Trevor Walker, David Page, JUDE W. SHAVLIK · 2009
This paper introduces a new type of application for called Bootstrapped Learning (BL). BL brings several challenges to ILP, including the need to (a) automate the ILP setup problem, (b) exploit the fact that a well-meaning teacher is providing pedagogically chosen examples and may be offering hints, (c) deal with small numbers of training examples and sometimes no explicit negative examples; and (d) bootstrap, i.e., to automatically base learning in part on the results of earlier learning sessions.