Three different forrnalizations of concept-learning in logic (as well as some variants) are analyzed and related. It is shown that learning from interpretations reduces to learning from entailment, which in turn reduces to learning from satisfiability. The implications of this result for inductive logic programming and computational learning theory are then discussed, and guidelines for choosin...

When labeled examples are not readily available, active learning and transfer learning are separate efforts to obtain labeled examples for inductive learning. Active learning asks domain experts to label a small set of examples, but there is a cost incurred for each answer. While transfer learning could borrow labeled examples from a different domain without incurring any labeling cost, there i...

Abstract Under what conditions does machine learning (ML) model opacity inhibit the possibility of explaining and understanding phenomena? In this article, I argue that nonepistemic values give shape to ML problem even if we keep researcher interests fixed. Treating models as an instance doing model-based science explain understand phenomena reveals there is (i) external problem, where presence...

This paper is a study of the problem of relevance in inductive concept learning. It gives definitions of irrelevant literals and irrelevant examples and presents ecient algorithms that enable their elimination. The proposed approach is directly applicable in propositional learning and in relation learning tasks that can be solved using a LINUS transformation approach. A simple inductive logic ...

We develop kernels for measuring the similarity between relational instances using background knowledge expressed in first-order logic. The method allows us to bridge the gap between traditional inductive logic programming (ILP) representations and statistical approaches to supervised learning. Logic programs are first used to generate proofs of given visitor programs that use predicates declar...

In the recent theoretical research activity of inductive learning, in particular, of inductive inference, Angluin has introduced the model of learning called minimally adequate teacher (MAT), that is, the model of learning via membership queries and equivalence queries, and has shown that the class of regular languages is e ciently learnable using deterministic nite automata (DFAs) (Angluin 198...

Machine Learning methods seem to help for model-building in the eld of Systems Theory. In this work, we present a study on a method for automatically inducing a discrete event structure (DEVS) from descriptions of behaviours of a system. To this end, both inductive learning and DEVS formalisms have been made compatible in order to translate input data into a form usable by the inductor. Morover...