Repository of University of Nova Gorica

Show document
A+ | A- | Help | SLO | ENG

Title:Explicit Feature Construction and Manipulation for Covering Rule Learning Algorithms
Authors:ID Lavrač, Nada, Jozef Stefan Institute and University of Nova Gorica (Author)
ID Fuernkranz, Johannes, Technische Universitaet Darmstat, Germany (Author)
ID Gamberger, Dragan, Rudjer Boskovic Institute, Croatia (Author)
Files: This document has no files that are freely available to the public. This document may have a physical copy in the library of the organization, check the status via COBISS. Link is opened in a new window
Language:English
Work type:Not categorized
Typology:1.16 - Independent Scientific Component Part or a Chapter in a Monograph
Organization:UNG - University of Nova Gorica
Abstract:Features are the main rule building blocks for rule learning algorithms. They can be simple tests for attribute values or complex logical terms representing available domain knowledge. In contrast to common practice in classification rule learning, we argue that separation of the feature construction and rule construction processes has theoretical and practical justification. Explicit usage of features enables a unifying framework of both propositional and relational rule learning and we present and analyze procedures for feature construction in both types of domains. It is demonstrated that the presented procedure for constructing a set of simple features has the property that the resulting set enables construction of complete and consistent rules whenever it is possible, and that the set does not include obviously irrelevant features. Additionally, the concept of feature relevancy is important for the effectiveness of rule learning. It this work, we illustrate the concept in the coverage space and prove that the relative relevancy has the quality-preserving property in respect to the resulting rules. Moreover, we show that the transformation from the attribute to the feature space enables a novel, theoretically justified way of handling unknown attribute values. The same approach enables that estimated imprecision of continuous attributes can be taken into account, resulting in construction of robust features in respect to this imprecision.
Keywords:Machine learning, Feature construction, Rule learning, Unknown attribute values
Publication status:Published
Year of publishing:2010
Number of pages:26
PID:20.500.12556/RUNG-3246 New window
COBISS.SI-ID:4843771 New window
DOI:10.1007/978-3-642-05177-7_6 New window
NUK URN:URN:SI:UNG:REP:OI29IXGR
Publication date in RUNG:14.07.2017
Views:5136
Downloads:0
Metadata:XML DC-XML DC-RDF
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Record is a part of a monograph

Title:Advances in Machine Learning I : Dedicated to the memory of professor Ryszard S. Michalski
Editors:Jacek Koronacki, Zbigniew W Ras, Sĺawomir T. Wierzchoń, Janusz Kacprzyk
Place of publishing:Berlin Heidelberg
Publisher:Springer Verlag
Year of publishing:2010
ISBN:978-3-642-05176-0

Back