Logical characterisations of inductive learning

Peter Flach, Gabbay Dov M., Kruse Rudolf

Research output: Chapter in Book/Report/Conference proceedingChapter in a book

Abstract

This chapter presents a logical analysis of induction. Contrary to common approaches to inductive logic that treat inductive validity as a real-valued generalisation of deductive validity, we argue that the only logical step in induction lies in hypothesis \em generation rather than evaluation. Inspired by the seminal paper of Kraus, Lehmann and Magidor we analyse the logic of inductive hypothesis generation on the meta-level of consequence relations. Two main forms of induction are considered: explanatory induction, aimed at inducing a general theory explaining given observations, and confirmatory induction, aimed at characterising completely or partly observed models. Several sets of meta-theoretical properties of inductive consequence relations are considered, each of them characterised by a suitable semantics. The approach followed in this chapter is extensively motivated by referring to recent and older work in philosophy, logic, and machine learning.
Translated title of the contributionLogical characterisations of inductive learning
Original languageEnglish
Title of host publicationHandbook of defeasible reasoning and uncertainty management systems, Vol. 4: Abductive reasoning and learning
EditorsDov M. Gabbay, Rudolf Kruse
PublisherKluwer Academic Publishers
Pages155 - 196
Number of pages41
ISBN (Print)0792365658
Publication statusPublished - 2000

Bibliographical note

Other page information: 155-196
Other identifier: 1000523

Fingerprint Dive into the research topics of 'Logical characterisations of inductive learning'. Together they form a unique fingerprint.

Cite this