One-sided instance-based boundary sets

EN Smirnov*, IG Sprinkhuizen-Kuyper, HJ van den Herik

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

Abstract

Instance retraction is a difficult problem for concept learning by version spaces. This chapter introduces a family of version-space representations called one-sided instance-based boundary sets. They are correct and efficiently computable representations for admissible concept languages. Compared to other representations, they are the most efficient useful(1) version-space representations for instance retraction.

Original languageEnglish
Title of host publicationDatabase Support for Data Mining Applications
Subtitle of host publicationDiscovering Knowledge with Inductive Queries
EditorsR Meo, PL Lanzi, M Klemettinen
PublisherSpringer Verlag
Pages270-288
Number of pages19
ISBN (Electronic)978-3-540-44497-8
ISBN (Print)978-3-540-22479-2
DOIs
Publication statusPublished - 2004

Publication series

SeriesLecture Notes in Computer Science
Volume2682
ISSN0302-9743

Cite this