Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches

Talha M. Amin; Igor Chikalov; Mikhail Moshkov; Beata Zielosko

doi:10.1007/978-3-642-37343-5_5

Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches

Talha M. Amin, Igor Chikalov, Mikhail Moshkov, Beata Zielosko

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

In the paper, we present a comparison of dynamic programming and greedy approaches for construction and optimization of approximate decision rules relative to the number of misclassifications. We use an uncertainty measure that is a difference between the number of rows in a decision table T and the number of rows with the most common decision for T. For a nonnegative real number γ, we consider γ-decision rules that localize rows in subtables of T with uncertainty at most γ. Experimental results with decision tables from the UCI Machine Learning Repository are also presented. © 2013 Springer-Verlag.

Original language	English (US)
Title of host publication	Knowledge Engineering, Machine Learning and Lattice Computing with Applications
Publisher	Springer Nature
Pages	41-50
Number of pages	10
ISBN (Print)	9783642373428
DOIs	https://doi.org/10.1007/978-3-642-37343-5_5
State	Published - 2013

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-642-37343-5_5

Cite this

@inproceedings{60e9fc96d71e490c9889b69af17d9608,

title = "Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches",

abstract = "In the paper, we present a comparison of dynamic programming and greedy approaches for construction and optimization of approximate decision rules relative to the number of misclassifications. We use an uncertainty measure that is a difference between the number of rows in a decision table T and the number of rows with the most common decision for T. For a nonnegative real number γ, we consider γ-decision rules that localize rows in subtables of T with uncertainty at most γ. Experimental results with decision tables from the UCI Machine Learning Repository are also presented. {\textcopyright} 2013 Springer-Verlag.",

author = "Amin, {Talha M.} and Igor Chikalov and Mikhail Moshkov and Beata Zielosko",

note = "KAUST Repository Item: Exported on 2020-10-01",

year = "2013",

doi = "10.1007/978-3-642-37343-5_5",

language = "English (US)",

isbn = "9783642373428",

pages = "41--50",

booktitle = "Knowledge Engineering, Machine Learning and Lattice Computing with Applications",

publisher = "Springer Nature",

}

Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches. / Amin, Talha M.; Chikalov, Igor; Moshkov, Mikhail et al.
Knowledge Engineering, Machine Learning and Lattice Computing with Applications. Springer Nature, 2013. p. 41-50.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches

AU - Amin, Talha M.

AU - Chikalov, Igor

AU - Moshkov, Mikhail

AU - Zielosko, Beata

N1 - KAUST Repository Item: Exported on 2020-10-01

PY - 2013

Y1 - 2013

N2 - In the paper, we present a comparison of dynamic programming and greedy approaches for construction and optimization of approximate decision rules relative to the number of misclassifications. We use an uncertainty measure that is a difference between the number of rows in a decision table T and the number of rows with the most common decision for T. For a nonnegative real number γ, we consider γ-decision rules that localize rows in subtables of T with uncertainty at most γ. Experimental results with decision tables from the UCI Machine Learning Repository are also presented. © 2013 Springer-Verlag.

AB - In the paper, we present a comparison of dynamic programming and greedy approaches for construction and optimization of approximate decision rules relative to the number of misclassifications. We use an uncertainty measure that is a difference between the number of rows in a decision table T and the number of rows with the most common decision for T. For a nonnegative real number γ, we consider γ-decision rules that localize rows in subtables of T with uncertainty at most γ. Experimental results with decision tables from the UCI Machine Learning Repository are also presented. © 2013 Springer-Verlag.

UR - http://hdl.handle.net/10754/564643

UR - http://link.springer.com/10.1007/978-3-642-37343-5_5

UR - http://www.scopus.com/inward/record.url?scp=84875863729&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-37343-5_5

DO - 10.1007/978-3-642-37343-5_5

M3 - Conference contribution

SN - 9783642373428

SP - 41

EP - 50

BT - Knowledge Engineering, Machine Learning and Lattice Computing with Applications

PB - Springer Nature

ER -

Optimization of approximate decision rules relative to number of misclassifications: Comparison of greedy and dynamic programming approaches

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this