Communications of the ACM
Learning Conjunctions of Horn Clauses
Machine Learning - Computational learning theory
First-order jk-clausal theories are PAC-learnable
Artificial Intelligence
Getting more out of programming-by-demonstration
Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Learning horn definitions: theory and an application to planning
New Generation Computing - Special issue on inductive logic programming 97
Learning Function-Free Horn Expressions
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Machine Learning
Machine Learning
Learning First-Order Acyclic Horn Programs from Entailment
ILP '98 Proceedings of the 8th International Workshop on Inductive Logic Programming
Learning Horn Expressions with LOGAN-H
The Journal of Machine Learning Research
Separating models of learning with faulty teachers
Theoretical Computer Science
Hi-index | 0.00 |
We study the problem of exact learning of first-order definite theories via queries, toward the goal of allowing humans to more efficiently teach first-order concepts to computers. Prior work has shown that first order Horn theories can be learned using a polynomial number of membership and equivalence queries [6]. However, these query types are sometimes unnatural for humans to answer and only capture a small fraction of the information that a human teacher might be able to easily communicate. In this work, we enrich the types of information that can be provided by a human teacher and study the associated learning problem from a theoretical perspective. First, we consider allowing queries that ask the teacher for the relevant objects in a training example. Second, we examine a new query type, called a pairing query, where the teacher provides mappings between objects in two different examples. We present algorithms that leverage these new query types as well as restrictions applied to equivalence queries to significantly reduce or eliminate the required number of membership queries, while preserving polynomial learnability. In addition, we give learnability results for certain cases of imperfect teachers. These results show, in theory, the potential for incorporating object-based queries into first-order learning algorithms in order to reduce human teaching effort.